© 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. 142729
    Prev
    Next
    INDEX
    Explanations

    :

    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
    Fixture
    -0.27
     explodes
    -0.27
    _Pre
    -0.27
     Junction
    -0.27
    .Pre
    -0.26
     Fixture
    -0.24
    ç¿©
    -0.24
    éra
    -0.23
     enormously
    -0.23
    æ·±ãģĦ
    -0.23
    POSITIVE LOGITS
    åĽ¢å§Ķ
    0.29
    obi
    0.28
    opal
    0.27
    oku
    0.27
    ctrl
    0.26
    yst
    0.25
    agli
    0.25
    tam
    0.25
    oru
    0.25
     repeat
    0.25
    Activations Density 2.639%

    No Known Activations