© 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. 108013
    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
    EH
    -0.28
    æł¹æį®ä¸įåIJĮ
    -0.26
    åīįæīĢ
    -0.25
     shutting
    -0.25
    åīįæĸ¹
    -0.24
    eh
    -0.24
     unl
    -0.24
     swallowed
    -0.24
    路线
    -0.24
    ç´IJ
    -0.23
    POSITIVE LOGITS
    acob
    0.28
    æľį
    0.27
    ì§ij
    0.27
    æĶ¶
    0.25
    odka
    0.25
    naires
    0.25
    _cv
    0.24
    achts
    0.24
    _IOCTL
    0.23
    oods
    0.23
    Activations Density 2.221%

    No Known Activations

    This feature has no known activations.