© 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. 30-TRANSCODER-HP
    7. 95162
    Prev
    Next
    INDEX
    Explanations

    body parts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    <decltype
    -0.30
    æĭĺçķĻ
    -0.29
    rede
    -0.29
     det
    -0.27
    ivist
    -0.27
    calcul
    -0.26
    ede
    -0.25
    det
    -0.25
     inland
    -0.25
    ä¸īåįĥ
    -0.25
    POSITIVE LOGITS
    èĤ©
    0.40
     arms
    0.40
    åĽ´
    0.39
     arm
    0.37
    èĤ©èĨĢ
    0.36
     wings
    0.34
    æīĭèĩĤ
    0.33
     shoulders
    0.33
    èħ°
    0.33
     hips
    0.32
    Activations Density 0.954%

    No Known Activations