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. 19-RESID-POST-AA
    6. 24183
    Prev
    Next
    INDEX
    Explanations

    Statistics and percentages

    np_max-act-logits · gemini-2.0-flash
    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
    ול
    -0.08
     Glad
    -0.08
    镄
    -0.07
     resett
    -0.07
     spontaneous
    -0.07
     Lind
    -0.07
     Cũng
    -0.07
    زراعة
    -0.07
    forced
    -0.07
     fullfile
    -0.07
    POSITIVE LOGITS
    🏓
    0.07
     each
    0.07
    判断
    0.07
    发现了
    0.07
    ㄡ
    0.07
    _picker
    0.06
    '])){
    ↵
    0.06
     `↵
    0.06
     offending
    0.06
    coffee
    0.06
    Activations Density 0.047%

    No Known Activations