© 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. 107318
    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
    èĢĮ
    -0.28
    ing
    -0.28
     bas
    -0.26
    3
    -0.26
     Bas
    -0.25
    bas
    -0.25
     while
    -0.25
     whereas
    -0.25
    .SM
    -0.25
    çĻ»
    -0.24
    POSITIVE LOGITS
    åIJĪä½ľåħ³ç³»
    0.24
    æ´
    0.24
     Contributors
    0.23
    ears
    0.23
     '\''
    0.23
    icine
    0.23
    对åŃ©åŃIJ
    0.23
     kê
    0.23
    äºĮæīĭ
    0.23
    æ¯Ķè¾ĥ好
    0.23
    Activations Density 2.012%

    No Known Activations

    This feature has no known activations.