© 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. 64348
    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
    addock
    -0.27
    arsers
    -0.25
     presente
    -0.25
    ponents
    -0.24
    praak
    -0.24
    vig
    -0.24
    apt
    -0.23
     Apt
    -0.23
    ripp
    -0.23
    pot
    -0.23
    POSITIVE LOGITS
    è¯įæĿ¡
    0.29
    urat
    0.29
    laps
    0.27
    alem
    0.26
    ê°ģ
    0.25
     Crowley
    0.25
    åŁİå¸Ĥ建设
    0.24
    oref
    0.23
    åŁİå¸Ĥåıijå±ķ
    0.23
     budd
    0.23
    Activations Density 0.576%

    No Known Activations

    This feature has no known activations.