© 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. 129923
    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
    @(
    -0.28
    座
    -0.27
    åķĨæĬ¥
    -0.27
    ä¹ĺåĿIJ
    -0.25
    nodiscard
    -0.25
    indo
    -0.25
    ɨ
    -0.24
    ä¸įæķ¢
    -0.24
    è¯ĨåĪ«
    -0.24
    ä½ĵéªĮ
    -0.24
    POSITIVE LOGITS
    女åŃIJ
    0.28
    anut
    0.26
    çĶ·åŃIJ
    0.26
    [section
    0.26
    outs
    0.25
     nail
    0.24
     anarchists
    0.24
     boiled
    0.23
    èĻ
    0.23
     madness
    0.23
    Activations Density 6.306%

    No Known Activations

    This feature has no known activations.