© 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. 141675
    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
    onth
    -0.29
    çĥŃæĥħ
    -0.27
    çļĦçĥŃæĥħ
    -0.27
    bundle
    -0.25
    ais
    -0.25
    表éĿ¢ä¸Ĭ
    -0.25
    ä»įæĺ¯
    -0.25
     bó
    -0.25
    家æĹı
    -0.24
    ä¾ĿçĦ¶æĺ¯
    -0.24
    POSITIVE LOGITS
    este
    0.29
    .nz
    0.27
    大家åĪĨ享
    0.27
    éĵ¢
    0.26
     subtitles
    0.26
    imes
    0.25
    IME
    0.25
     sovereign
    0.25
    subs
    0.24
    apia
    0.24
    Activations Density 32.992%

    No Known Activations

    This feature has no known activations.