© 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. 64248
    Prev
    Next
    INDEX
    Explanations

    announcements or news

    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
     dissolved
    -0.28
     Favor
    -0.27
    ingham
    -0.26
    rise
    -0.25
    çĶ¨èĩªå·±çļĦ
    -0.25
     Thông
    -0.25
    ä¸ĢåĪĨéĴ±
    -0.24
    è´µ
    -0.24
     affirmative
    -0.24
     favor
    -0.24
    POSITIVE LOGITS
    ashi
    0.28
    è´»
    0.25
     Nielsen
    0.23
     Plat
    0.23
     NSAttributedString
    0.23
    æĭ¥
    0.22
     Cant
    0.22
    .registry
    0.22
    ç»
    0.22
    Median
    0.22
    Activations Density 10.592%

    No Known Activations