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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 15-RESID-POST-AA
    6. 60270
    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
     khổ
    -0.08
    戰
    -0.07
    asis
    -0.07
    试卷
    -0.07
    奶奶
    -0.07
    HIR
    -0.07
    mathrm
    -0.07
    	w
    -0.07
    Ń
    -0.07
    مى
    -0.06
    POSITIVE LOGITS
     ///</
    0.07
     gốc
    0.07
    incerely
    0.07
     Forex
    0.07
    solid
    0.07
    .AddScoped
    0.07
    /oct
    0.07
     המק
    0.07
    hooks
    0.07
     unos
    0.07
    Activations Density 0.000%

    No Known Activations