© 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. 63526
    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
     quarter
    -0.28
    伪
    -0.27
    è´µ
    -0.26
    /wp
    -0.26
     Sac
    -0.24
    ifle
    -0.24
    é«ĺåİĭ
    -0.24
    æľĪ
    -0.23
    sein
    -0.23
    è·ĸ
    -0.23
    POSITIVE LOGITS
    onium
    0.26
    once
    0.26
     TAG
    0.26
    vens
    0.24
    éķ³
    0.24
    åĪ°è¿ĻéĩĮ
    0.24
    å¾½
    0.24
    aff
    0.24
     here
    0.24
    _history
    0.23
    Activations Density 42.746%

    No Known Activations

    This feature has no known activations.