© 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. 23393
    Prev
    Next
    INDEX
    Explanations

    challenge

    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
    累积
    -0.29
    åħ¨å¥Ĺ
    -0.28
    Callback
    -0.28
    æ¥Ķ
    -0.27
    丢失
    -0.26
    _callback
    -0.26
    ocal
    -0.25
    CallBack
    -0.25
    Cal
    -0.24
    _CAL
    -0.23
    POSITIVE LOGITS
    [".
    0.26
    besch
    0.26
    为ä¾ĭ
    0.26
    ADR
    0.24
     Giz
    0.24
    |=↵
    0.24
    çĨĻ
    0.24
    ese
    0.24
    apiro
    0.23
     explosive
    0.23
    Activations Density 0.001%

    No Known Activations