© 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. 107590
    Prev
    Next
    INDEX
    Explanations

    Code snippets

    np_max-act · gemini-2.0-flash
    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
    eni
    -0.26
    Ĥ¨
    -0.26
    tensor
    -0.25
    uffle
    -0.25
    çĶ°
    -0.25
     ign
    -0.25
     Bucket
    -0.25
     гÑĢаж
    -0.25
    çļ¿
    -0.24
    ений
    -0.24
    POSITIVE LOGITS
    NOP
    0.27
    obl
    0.25
    ông
    0.25
    cala
    0.25
    踩
    0.24
    è¿ĶåĽŀæIJľçĭIJ
    0.24
    ners
    0.24
    并éĢļè¿ĩ
    0.24
    _union
    0.24
    æīĵéĢļ
    0.24
    Activations Density 0.234%

    No Known Activations