© 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. 12-TRANSCODER-HP
    7. 23105
    Prev
    Next
    INDEX
    Explanations

    men

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    姣
    -0.33
    FI
    -0.27
     "\",
    -0.26
    ä¸ĭè°ĥ
    -0.25
    æĽ²çº¿
    -0.25
    ä¸ĭ车
    -0.25
    erties
    -0.25
     entityType
    -0.24
    ablo
    -0.23
    ân
    -0.23
    POSITIVE LOGITS
    http
    0.26
    chap
    0.26
    åijĨ
    0.25
    ä½ľèĢħæīĢæľī
    0.24
    éĻ¤å¤ĸ
    0.24
    ä¿ĿçķĻ
    0.24
     Rouge
    0.23
    avel
    0.23
     Ed
    0.23
    âĸ²
    0.23
    Activations Density 0.025%

    No Known Activations