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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11-RESID-POST-AA
    11. 77991
    Prev
    Next
    INDEX
    Explanations

    animal care

    np_max-act · gemini-2.0-flash

    tokens that address the reader or use second-person/reader-directed language (e.g., "you", "your", "we" used to speak to the reader).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .connect
    -0.07
    ای
    -0.07
    IZE
    -0.07
     Libyan
    -0.07
    外交
    -0.06
    annie
    -0.06
     artık
    -0.06
    .From
    -0.06
     mùa
    -0.06
    ROWN
    -0.06
    POSITIVE LOGITS
     oversh
    0.07
     Reflex
    0.07
    .choices
    0.07
    lor
    0.07
     �
    0.07
    別人
    0.07
    喝酒
    0.07
    thr
    0.07
     Invocation
    0.07
     TAS
    0.07
    Activations Density 0.259%

    No Known Activations