© 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. 63544
    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
     boundaries
    -0.31
    resar
    -0.26
    ç¡Į
    -0.25
    stim
    -0.25
    lest
    -0.25
     Bound
    -0.25
    ">',↵
    -0.25
    athing
    -0.25
    andre
    -0.25
     Stim
    -0.24
    POSITIVE LOGITS
    wich
    0.29
     applications
    0.27
    åĨĪ
    0.27
    åºĶåľ¨
    0.27
    ill
    0.25
    ä¹ĭä¸ĭ
    0.25
    tica
    0.25
    capability
    0.24
    astes
    0.23
    emen
    0.23
    Activations Density 10.004%

    No Known Activations

    This feature has no known activations.