© 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. 22440
    Prev
    Next
    INDEX
    Explanations

    Technical/Scientific texts

    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
    erate
    -0.28
    dia
    -0.28
    uye
    -0.25
    adal
    -0.25
    ä¸ĵå±ŀ
    -0.24
    vro
    -0.24
    å¥ĭè¿Ľ
    -0.24
    æij¸ç´¢
    -0.24
    side
    -0.24
    _inside
    -0.24
    POSITIVE LOGITS
    转载
    0.29
    icação
    0.25
    ict
    0.25
     Heard
    0.24
    éĺ¡
    0.24
    æ¶Īè´¹
    0.24
    neck
    0.24
     js
    0.23
    order
    0.23
    ICON
    0.23
    Activations Density 0.000%

    No Known Activations