© 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. 149789
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ланд
    -0.28
    ickness
    -0.25
    游æĪıä¸Ń
    -0.25
    à¥į
    -0.25
    çģ«çĥ§
    -0.24
    ioned
    -0.24
    ä¸Ĭåįĥ
    -0.24
    fad
    -0.23
    ULO
    -0.23
    Mas
    -0.23
    POSITIVE LOGITS
    atar
    0.26
    omite
    0.25
    æݢ究
    0.24
    æĢĢ
    0.24
    ORIGINAL
    0.24
    onas
    0.24
    ä¹ĭæīĢ
    0.23
     Sudoku
    0.23
    ORD
    0.23
    èĩªå®¶
    0.23
    Activations Density 0.183%

    No Known Activations

    This feature has no known activations.