© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 53938
    Prev
    Next
    INDEX
    Explanations

    Erik, Ecma, EOL

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ned
    -0.10
    æµ·è¾¹
    -0.10
    pute
    -0.10
    追究
    -0.10
    -eslint
    -0.10
    lot
    -0.10
    icip
    -0.09
    ver
    -0.09
    ı
    -0.09
    _e
    -0.09
    POSITIVE LOGITS
    /disable
    0.19
     dÃłng
    0.15
    uated
    0.13
    дин
    0.13
    ymology
    0.12
    hardt
    0.12
    uating
    0.12
    peror
    0.12
    oteric
    0.11
    MBED
    0.11
    Activations Density 1.793%

    No Known Activations