© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 129975
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Not in Any Lists

    No Comments

    Negative Logits
    dense
    -0.29
    å¢ħ
    -0.28
     Citation
    -0.26
    åħ¶ä½Ļ
    -0.25
    ++↵↵
    -0.24
    _density
    -0.24
    /details
    -0.24
     intl
    -0.24
    æĶ¾å¤§
    -0.24
     dense
    -0.24
    POSITIVE LOGITS
    å¥Ķ
    0.27
    uder
    0.27
    广
    0.27
     Vet
    0.26
    .MM
    0.26
     chù
    0.25
     rolled
    0.25
    VED
    0.25
    APER
    0.25
    aper
    0.25
    Activations Density 9.766%

    No Known Activations

    This feature has no known activations.