© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 35532
    Prev
    Next
    INDEX
    Explanations

    on, at, over + measurement/quantity

    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
    routine
    -0.09
    åĽ´å¢Ļ
    -0.09
    åĩĮæĻ¨
    -0.09
    éĢIJ
    -0.09
    ENDOR
    -0.09
    æĪijä»¬ä¹Ł
    -0.08
    .lib
    -0.08
    abbo
    -0.08
    ç¼ĺ
    -0.08
    ,readonly
    -0.08
    POSITIVE LOGITS
    ä½İ温
    0.09
    èijĨ
    0.09
     Emm
    0.08
    æĬķèµĦé¢Ŀ
    0.08
    æĺı
    0.08
    éľı
    0.08
    è¿IJç»´
    0.08
     tilt
    0.08
    æķ£
    0.08
    plen
    0.08
    Activations Density 0.020%

    No Known Activations