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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 23240
    Prev
    Next
    INDEX
    Explanations

    commas, quotation marks

    np_max-act · gemini-2.0-flash
    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
     Crypt
    -0.07
    ensitivity
    -0.07
    arg
    -0.07
    实质性
    -0.07
    鸟类
    -0.06
    нак
    -0.06
    持
    -0.06
    منع
    -0.06
    _listen
    -0.06
     shorten
    -0.06
    POSITIVE LOGITS
    Medium
    0.07
    оборот
    0.07
    ɑ
    0.07
     PHOTO
    0.07
    KO
    0.07
    .MiddleLeft
    0.07
    ɔ
    0.06
     Premiere
    0.06
    .old
    0.06
     rơi
    0.06
    Activations Density 0.095%

    No Known Activations