© 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. 38534
    Prev
    Next
    INDEX
    Explanations

    BM, BMP, or bitmap prefixes

    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
    ä¸įåħĭ
    -0.10
    ç»İ
    -0.10
    ous
    -0.10
    ä¼į
    -0.10
    ç¼ľ
    -0.10
    ç¢Ľ
    -0.09
    åIJģ
    -0.09
    ãĥ³
    -0.09
    ç½ķ
    -0.09
    éŨæĪ·ç½ijç«Ļ
    -0.09
    POSITIVE LOGITS
    bak
    0.09
    IVES
    0.08
    SUP
    0.08
    upert
    0.08
    èĮİ
    0.08
     rem
    0.08
    ucch
    0.08
    INGS
    0.08
    è¿ĻåĿĹ
    0.08
    ives
    0.08
    Activations Density 0.010%

    No Known Activations