© 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. 7-RESID-POST-AA
    11. 9678
    Prev
    Next
    INDEX
    Explanations

    media

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     renting
    -0.09
     vas
    -0.07
     determinant
    -0.07
    Led
    -0.07
     Clint
    -0.07
     melodies
    -0.07
     phantom
    -0.07
    儳
    -0.07
    CON
    -0.07
    崔
    -0.07
    POSITIVE LOGITS
     тыс
    0.08
    .vue
    0.07
    丟
    0.07
     bụ
    0.07
    ⵢ
    0.07
    供暖
    0.06
    伸び
    0.06
     Hubb
    0.06
    ーム
    0.06
    بية
    0.06
    Activations Density 0.003%

    No Known Activations