© 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. 31-TRANSCODER-HP
    7. 19930
    Prev
    Next
    INDEX
    Explanations

    XML code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    _legend
    -0.28
    ä»ģ
    -0.26
    legend
    -0.26
    åįĥ
    -0.25
    ten
    -0.24
    éĴ±
    -0.24
    说çļĦæĺ¯
    -0.23
    æĽ·
    -0.23
     diamonds
    -0.23
    综åIJĪä½ĵ
    -0.23
    POSITIVE LOGITS
     Carp
    0.33
    å½ķ
    0.32
     line
    0.29
    -line
    0.29
     Line
    0.28
    pline
    0.28
    sut
    0.27
    -Line
    0.27
    jour
    0.27
    æĬļæij¸
    0.27
    Activations Density 0.305%

    No Known Activations