© 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. 141933
    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
     Inflate
    -0.28
     Resume
    -0.27
    ORY
    -0.27
    éĥ¨ä»½
    -0.26
    æľ¦
    -0.26
    åĬ¨éĿĻ
    -0.25
    naires
    -0.25
     oneself
    -0.25
    semb
    -0.24
    reveal
    -0.24
    POSITIVE LOGITS
     nonlinear
    0.26
     frank
    0.26
    ayed
    0.25
    åĪĩåī²
    0.25
     fut
    0.25
    colo
    0.24
    .twig
    0.23
     futuro
    0.23
    梦幻
    0.23
    >n
    0.23
    Activations Density 10.361%

    No Known Activations

    This feature has no known activations.