© 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. 108317
    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
    езн
    -0.25
     camer
    -0.25
     suff
    -0.25
    COPE
    -0.25
    zon
    -0.25
    /includes
    -0.25
    CAM
    -0.24
    /mac
    -0.24
    _NB
    -0.24
    骼
    -0.24
    POSITIVE LOGITS
    éĩį
    0.27
    çīĪæľ¬
    0.25
    èķ¨
    0.25
    èĢĮåĩº
    0.25
    -fed
    0.25
    æŧ
    0.24
     edition
    0.24
    еÑĩен
    0.24
    å·¥ä½ľæķĪçİĩ
    0.23
    éĥ¨åĪĨ
    0.23
    Activations Density 5.422%

    No Known Activations

    This feature has no known activations.