© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 28754
    Prev
    Next
    INDEX
    Explanations

    First-person narratives

    np_max-act · gemini-2.0-flash

    requests or statements about personal identity, experiences, preferences, or daily routines—i.e., self-referential biography and “you/I” lifestyle talk.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    StrictEqual
    -0.08
    これは
    -0.07
    .DESC
    -0.07
    非常好的
    -0.07
     chose
    -0.07
    .Collections
    -0.07
    もちろ
    -0.07
    かった
    -0.07
    Illegal
    -0.07
    مف
    -0.07
    POSITIVE LOGITS
    Ἕ
    0.08
    istema
    0.07
     splitter
    0.07
    emes
    0.07
     lawful
    0.07
    ynam
    0.07
     rapper
    0.07
     stylish
    0.07
     Ae
    0.07
     �
    0.06
    Activations Density 0.238%

    No Known Activations