© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 12-TRANSCODER-HP
    7. 22004
    Prev
    Next
    INDEX
    Explanations

    Fed

    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
    Negative Logits
    缮çļĦ
    -0.27
    Allowed
    -0.27
    ikel
    -0.26
    odzi
    -0.26
    干货
    -0.25
    &A
    -0.25
    ods
    -0.25
    division
    -0.24
     success
    -0.24
    FORMAT
    -0.24
    POSITIVE LOGITS
    åįĬ个
    0.29
    ductor
    0.28
    éĴ¢
    0.27
    åIJĦè¡ĮåIJĦ
    0.27
    ReadStream
    0.26
    amer
    0.26
    .Tick
    0.26
    STER
    0.25
    ĵį
    0.25
    BuildContext
    0.25
    Activations Density 0.010%

    No Known Activations