© 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. 23-TRANSCODER-HP
    7. 24519
    Prev
    Next
    INDEX
    Explanations

    units of measurement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     german
    -0.28
    绣çŃ¹æİ¨è¿Ľ
    -0.27
    ogl
    -0.26
    çħ³
    -0.25
     dragging
    -0.25
     lat
    -0.25
     excavation
    -0.25
    å¼ĢèįĴ
    -0.24
    ãĤ¹ãĤ¯
    -0.24
    sburg
    -0.24
    POSITIVE LOGITS
    大å¦Ī
    0.26
    (levels
    0.26
    æ°´å¹³
    0.25
    éĢĨ
    0.24
     Suit
    0.24
    追
    0.24
     Irma
    0.23
    (:,:,
    0.23
     каждÑĭй
    0.23
    astes
    0.23
    Activations Density 0.006%

    No Known Activations