© 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. 22-TRANSCODER-HP
    7. 113111
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ä¸įæĪIJ
    -0.27
    åĥ§
    -0.27
    cks
    -0.26
    und
    -0.25
    ÅĽcie
    -0.25
     underst
    -0.25
    ç³Ĭ
    -0.25
    gor
    -0.25
    Dispose
    -0.24
    åĩłçĤ¹
    -0.24
    POSITIVE LOGITS
     Elev
    0.30
     elev
    0.26
    <|endoftext|>
    0.25
     (**
    0.25
     Marsh
    0.24
    (cur
    0.23
    åľ¨å¤ĸéĿ¢
    0.23
     elevation
    0.23
    ____
    0.23
    —we
    0.23
    Activations Density 0.013%

    No Known Activations