© 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. 76020
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     flew
    -0.07
    打破了
    -0.06
     бо
    -0.06
    +"/
    -0.06
    同时还
    -0.06
    占地面积
    -0.06
     inheritance
    -0.06
    可能性
    -0.06
    环境污染
    -0.06
    stringLiteral
    -0.06
    POSITIVE LOGITS
     Doesn
    0.08
    ציה
    0.07
    pons
    0.07
    Vien
    0.07
     저
    0.07
    -Day
    0.07
    agina
    0.06
    Function
    0.06
    February
    0.06
    .Headers
    0.06
    Activations Density 0.032%

    No Known Activations