© 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. 39886
    Prev
    Next
    INDEX
    Explanations

    code and programming

    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
     cour
    -0.10
    åħľ
    -0.09
    æĻ®éĢļ
    -0.08
    ç²¾ç»ĨåĮĸ
    -0.08
    cour
    -0.08
    _REDIRECT
    -0.08
    ç§ijåѦæĬĢæľ¯
    -0.08
     окÑĢÑĥг
    -0.07
    urtle
    -0.07
    Formats
    -0.07
    POSITIVE LOGITS
    代çłģ
    0.17
     code
    0.15
     код
    0.15
     ì½Ķëĵľ
    0.13
    ãĤ³ãĥ¼ãĥī
    0.12
    å¼Ģåıij
    0.12
    -code
    0.11
     código
    0.11
    ocode
    0.10
    UserCode
    0.10
    Activations Density 0.578%

    No Known Activations