© 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. 9-TRANSCODER-HP
    7. 30262
    Prev
    Next
    INDEX
    Explanations

    wiring

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    åĢĻ
    -0.33
     intern
    -0.27
    符åIJĪ
    -0.27
    assy
    -0.26
    ä¸į符åIJĪ
    -0.26
    çķĻä¸ĭ
    -0.26
    -sum
    -0.25
    oders
    -0.25
    akis
    -0.25
    illy
    -0.25
    POSITIVE LOGITS
     boosting
    0.27
    çĤ¹äºĨ
    0.27
    æĸĩä¸Ń
    0.26
    ationToken
    0.26
    åħ¥èĤ¡
    0.26
    .boost
    0.26
    eton
    0.25
     shred
    0.25
    arkin
    0.25
     membership
    0.24
    Activations Density 0.234%

    No Known Activations