© 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. 141160
    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
     cop
    -0.27
     Class
    -0.26
    Class
    -0.25
    antar
    -0.25
    ythe
    -0.24
    _CLASS
    -0.24
    ıè¿°
    -0.24
    anya
    -0.24
    onz
    -0.24
    anic
    -0.24
    POSITIVE LOGITS
     conceivable
    0.29
    ç»ĵåIJĪèµ·æĿ¥
    0.28
    综åIJĪæĢ§
    0.26
    æ´½
    0.26
    lox
    0.25
     traps
    0.25
     particular
    0.25
    便åĪ©åºĹ
    0.25
    auth
    0.24
    regist
    0.24
    Activations Density 28.979%

    No Known Activations

    This feature has no known activations.