© 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. 108470
    Prev
    Next
    INDEX
    Explanations

    for

    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
    禺
    -0.28
    endar
    -0.27
    åIJĦè¡ĮåIJĦ
    -0.27
    åIJĦæł·
    -0.26
    *size
    -0.25
    гон
    -0.25
    æ»ļçIJĥ
    -0.24
    lectron
    -0.24
     '$
    -0.24
    è¦ģçľĭ
    -0.24
    POSITIVE LOGITS
    ati
    0.29
    ลà¸Ńย
    0.28
    erti
    0.26
     fle
    0.26
     discipline
    0.25
    _.
    0.25
    _
    0.25
    Ă
    0.24
    ||
    0.24
     xuyên
    0.24
    Activations Density 1.076%

    No Known Activations