© 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. 107928
    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
    perm
    -0.29
    -form
    -0.28
    ÙĪع
    -0.26
    çĶº
    -0.26
    emento
    -0.25
    _form
    -0.25
    ä¸įåħ¬å¹³
    -0.25
     attendance
    -0.25
    èĴ´
    -0.25
    é«ĺãģı
    -0.25
    POSITIVE LOGITS
    æ±Ĥ
    0.25
    çļ®éĿ©
    0.25
    éļIJ
    0.25
    çļĦä¸Ģ项
    0.25
    æ½ľåľ¨
    0.24
    ä¸įåIJĮç±»åŀĭ
    0.24
    åįĬå¤ľ
    0.23
    驼
    0.23
    eni
    0.23
    æį¢
    0.23
    Activations Density 3.931%

    No Known Activations

    This feature has no known activations.