© 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. 107232
    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
    -cross
    -0.27
     crossed
    -0.27
     siêu
    -0.25
    è¶ħ
    -0.25
    Fast
    -0.24
    ä¸įå¼Ģ
    -0.24
     Fast
    -0.24
     exceeded
    -0.24
     EntityState
    -0.24
    æ¿Ĵ
    -0.24
    POSITIVE LOGITS
    åij³
    0.31
     aspir
    0.29
    éĤ£ä¸Ģ
    0.28
    çīĪæĿĥ声æĺİ
    0.28
    /preferences
    0.28
    rought
    0.26
    caught
    0.26
    çļĦéĤ£ä¸Ģ
    0.26
    çĿĢ
    0.25
    åIJĽåŃIJ
    0.24
    Activations Density 0.912%

    No Known Activations

    This feature has no known activations.