© 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. 10671
    Prev
    Next
    INDEX
    Explanations

    ML engine, RegExp, Exiv2, Exprtk

    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
    çİĭæľĿ
    -0.11
    åľ¨çĶŁæ´»ä¸Ń
    -0.10
    æĮĪ
    -0.09
    åľ¨å¤ĸéĿ¢
    -0.09
    å¸ĿåĽ½
    -0.09
    ç½´
    -0.08
    æ³£
    -0.08
    Scalars
    -0.08
    éĶĥ
    -0.08
    ORIZ
    -0.08
    POSITIVE LOGITS
    æĹ¢
    0.10
    isor
    0.10
    üm
    0.09
    onis
    0.09
    opers
    0.09
    å¥ĸ
    0.09
    acks
    0.09
    绩
    0.09
    é½IJ
    0.09
    öne
    0.09
    Activations Density 0.091%

    No Known Activations