© 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. 63362
    Prev
    Next
    INDEX
    Explanations

    Formal writing excerpts

    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
     stump
    -0.28
     wherever
    -0.27
    umper
    -0.26
    essim
    -0.26
    olumn
    -0.26
    è¾ľè´Ł
    -0.26
    æĹĹèĪ°
    -0.26
     felt
    -0.24
     organ
    -0.24
     tamp
    -0.24
    POSITIVE LOGITS
    ä¹ĭä¸Ģ
    0.28
    gency
    0.28
    è¿Ļ对
    0.26
    ÑĥÑİÑĤ
    0.26
     Lat
    0.26
    Lat
    0.25
    çŃĸ
    0.25
    arta
    0.25
    otic
    0.24
    ä¹ĭ
    0.24
    Activations Density 18.901%

    No Known Activations