© 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. 20-TRANSCODER-HP
    7. 106839
    Prev
    Next
    INDEX
    Explanations

    Narrative writing connecting words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    çļĦ人çī©
    -0.31
    _Params
    -0.31
    çļĦ人æĿ¥è¯´
    -0.30
    cue
    -0.30
     Executors
    -0.29
    责任人
    -0.29
    actors
    -0.28
    ("'",
    -0.27
    (SS
    -0.27
    ÃŃc
    -0.26
    POSITIVE LOGITS
    åĢį
    0.27
    械
    0.26
    ä¸įå¾Ĺ转载
    0.26
    å°ĸ
    0.25
    åij³
    0.24
     Grinding
    0.24
    anj
    0.24
    anje
    0.24
    åĿļ
    0.23
    ouver
    0.23
    Activations Density 29.352%

    No Known Activations