© 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. 23253
    Prev
    Next
    INDEX
    Explanations

    Physics and math

    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
    宪
    -0.28
    \Message
    -0.26
     nearby
    -0.25
    æ´¿
    -0.25
    åĬ²
    -0.25
    bral
    -0.24
    æ·±æ¸Ĭ
    -0.24
    uously
    -0.24
    [Math
    -0.23
     screwed
    -0.23
    POSITIVE LOGITS
    iston
    0.30
    ysi
    0.26
     ÑĥÑģп
    0.26
    Issue
    0.25
     Past
    0.25
    mere
    0.25
    ä¸ĢæĶ¯
    0.25
    ä¸Ģå°ģä¿¡
    0.24
    æľ¬ç½ij
    0.24
    è¿ĩåİ»
    0.24
    Activations Density 0.003%

    No Known Activations