© 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. 142722
    Prev
    Next
    INDEX
    Explanations

    Question and answer excerpts

    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
    inke
    -0.31
    ousse
    -0.26
     quant
    -0.25
    arter
    -0.25
    个å¤ļ
    -0.24
    工夫
    -0.24
    jian
    -0.24
    /environment
    -0.23
    OrFail
    -0.23
     quantity
    -0.23
    POSITIVE LOGITS
    _DER
    0.27
     —↵↵
    0.27
    _deriv
    0.27
     trackers
    0.26
     derivation
    0.26
    ROID
    0.26
    deriv
    0.25
    ä¸į容æĺĵ
    0.25
    engl
    0.25
     Der
    0.24
    Activations Density 7.383%

    No Known Activations