© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 25-TRANSCODER-HP
    7. 107950
    Prev
    Next
    INDEX
    Explanations

    questions and answers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     junior
    -0.26
    ...)↵
    -0.26
    .radians
    -0.26
    俺
    -0.25
    @student
    -0.25
    adians
    -0.25
     ...č↵
    -0.24
    -invalid
    -0.24
     "";č↵
    -0.24
    ","");↵
    -0.24
    POSITIVE LOGITS
    åľ¨æѤ
    0.26
    é¢Ĭ
    0.26
    _IB
    0.26
    帼
    0.25
    ç³Ļ
    0.25
    å®ĥ们
    0.25
    å°±è¿Ļæł·
    0.25
    éĺī
    0.25
    åĽłä¸ºä»ĸ们
    0.25
    å®ĥåı¯ä»¥
    0.24
    Activations Density 0.113%

    No Known Activations