© 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. 15826
    Prev
    Next
    INDEX
    Explanations

    code

    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_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
    蔫
    -0.07
    quelle
    -0.07
     Passport
    -0.07
    .fl
    -0.07
    INLINE
    -0.07
     transports
    -0.07
    劂
    -0.07
    ploy
    -0.07
     Pearl
    -0.06
    uelle
    -0.06
    POSITIVE LOGITS
    _Ex
    0.07
    理科
    0.07
    外部
    0.07
     والإ
    0.06
     字
    0.06
    文体
    0.06
    高低
    0.06
    理工
    0.06
    ding
    0.06
     office
    0.06
    Activations Density 0.052%

    No Known Activations