© 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. 130158
    Prev
    Next
    INDEX
    Explanations

    Computer code/technical writing

    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
    èģĶ
    -0.30
    ei
    -0.28
    ÑģÑĭ
    -0.27
    è¯ł
    -0.27
    imal
    -0.26
    ç§Ģ
    -0.26
    Speaker
    -0.25
     Mobil
    -0.24
    .parameter
    -0.24
    åįķ车
    -0.23
    POSITIVE LOGITS
    æİĸ
    0.26
    ,lat
    0.26
    ÇĴ
    0.25
     Ju
    0.25
     downloadable
    0.24
    管å±Ģ
    0.23
    妹åŃIJ
    0.23
    å¼ķæĵİ
    0.23
    妣
    0.23
    (lat
    0.23
    Activations Density 0.728%

    No Known Activations