© 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. 130535
    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
     Mild
    -0.27
    è¿ĻæĿ¡è·¯
    -0.26
    assistant
    -0.26
    phet
    -0.26
     mild
    -0.26
     improvement
    -0.25
     Equ
    -0.25
    antically
    -0.25
     equ
    -0.25
    osa
    -0.25
    POSITIVE LOGITS
     uncomp
    0.27
     compensate
    0.26
    .bat
    0.26
    åĢĴ
    0.26
    ALSE
    0.25
    大åħ¨
    0.25
    yeah
    0.25
    directories
    0.24
    urus
    0.24
     кÑĥÑĢÑģ
    0.24
    Activations Density 8.567%

    No Known Activations

    This feature has no known activations.