© 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. 107661
    Prev
    Next
    INDEX
    Explanations

    Academic/scientific publications

    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
    è§Ħæł¼
    -0.28
    æµİ
    -0.28
    DIV
    -0.27
    çļĦè¦ģæ±Ĥ
    -0.25
    åŁĭ
    -0.25
    æ¢Ń
    -0.24
    åıªè¦ģæĺ¯
    -0.23
    Began
    -0.23
    Inject
    -0.23
    çĿ¹
    -0.23
    POSITIVE LOGITS
     cram
    0.28
    berman
    0.26
    建设åĴĮ
    0.26
    zion
    0.24
    isi
    0.24
    stdin
    0.24
    åļı
    0.24
    zan
    0.24
     Last
    0.24
     Aust
    0.23
    Activations Density 5.903%

    No Known Activations