© 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. 30207
    Prev
    Next
    INDEX
    Explanations

    effort and difficulty

    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
     flare
    -0.28
    _hyper
    -0.26
     Cyber
    -0.26
    룬
    -0.26
    _fire
    -0.25
    éľŀ
    -0.24
    ker
    -0.24
    Outline
    -0.24
    ä¸ĵéŨ
    -0.24
     Fort
    -0.24
    POSITIVE LOGITS
     compos
    0.28
    morgan
    0.26
    çĶŁäº§è®¾å¤ĩ
    0.25
    engers
    0.25
    IsUnicode
    0.24
    ãģªãĤĵãģ¨
    0.24
    sprintf
    0.24
    multiline
    0.24
    让æ¶Īè´¹èĢħ
    0.24
     Mixing
    0.24
    Activations Density 0.267%

    No Known Activations