Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 130884
    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .Phone
    -0.07
    pet
    -0.07
     �
    -0.07
    מטופ
    -0.07
    规章制度
    -0.07
    党组织
    -0.07
    .Audio
    -0.07
     Hawk
    -0.06
    묻
    -0.06
     söz
    -0.06
    POSITIVE LOGITS
     gerade
    0.07
    (*
    0.07
    임
    0.07
     בעיקר
    0.07
    etrain
    0.07
    主要
    0.07
    interp
    0.07
    _singleton
    0.07
    岗
    0.06
     raster
    0.06
    Activations Density 0.284%

    No Known Activations