© 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. 64244
    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
    çķĻ
    -0.27
    被éªĹ
    -0.24
    phen
    -0.24
    oner
    -0.24
    èİ«
    -0.24
     Koch
    -0.24
    è·¨è¶Ĭ
    -0.23
    SOURCE
    -0.23
     Barnes
    -0.23
     bounds
    -0.22
    POSITIVE LOGITS
     integ
    0.29
    stra
    0.27
    路桥
    0.26
    è¯ļæĦı
    0.25
    åī¯éĻ¢éķ¿
    0.25
    åµ´
    0.25
    ercial
    0.25
     Pants
    0.24
    stras
    0.24
    еÑģÑĮ
    0.24
    Activations Density 21.410%

    No Known Activations

    This feature has no known activations.