© 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. 14-TRANSCODER-HP
    7. 41217
    Prev
    Next
    INDEX
    Explanations

    looking out a window

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ugi
    -0.30
    纳æĸ¯
    -0.28
    秩
    -0.28
    olated
    -0.27
    sup
    -0.27
     relations
    -0.27
    裸
    -0.26
     sup
    -0.26
    endar
    -0.25
     flush
    -0.25
    POSITIVE LOGITS
    æĿľ
    0.27
     wur
    0.26
    諮詢
    0.24
    .opend
    0.23
    hek
    0.23
    éĸĭå±ķ
    0.23
    .Never
    0.23
     UObject
    0.23
     ìŀĪê²Į
    0.23
    ÎĨ
    0.23
    Activations Density 0.400%

    No Known Activations