© 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. 24-TRANSCODER-HP
    7. 149900
    Prev
    Next
    INDEX
    Explanations

    free

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Plate
    -0.27
    quals
    -0.26
    é¹
    -0.26
     webpage
    -0.26
    æľ¬ç½ijç«Ļ
    -0.25
    ÑĤиÑĢов
    -0.25
    web
    -0.25
     Web
    -0.25
     website
    -0.25
    Cap
    -0.25
    POSITIVE LOGITS
    ellig
    0.29
    uell
    0.28
    ä¹ĭä¸Ĭ
    0.28
    erras
    0.28
    ENSOR
    0.27
    essen
    0.26
    hoc
    0.25
    èĥĮä¸Ĭ
    0.24
    åIJĪçIJĨçļĦ
    0.24
     finals
    0.24
    Activations Density 0.165%

    No Known Activations