© 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. 23503
    Prev
    Next
    INDEX
    Explanations

    åľ¨ä¹İ

    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
    fur
    -0.09
    æĺ¯æľĢ
    -0.08
    èĢģå¸ĪçļĦ
    -0.08
    åľ¨éĩĮéĿ¢
    -0.08
    åľ¨éĤ£éĩĮ
    -0.08
    æĺ¯è°ģ
    -0.08
    p
    -0.08
    åı¯æĥ³èĢĮçŁ¥
    -0.08
     mutil
    -0.07
    æĭľå¸Ī
    -0.07
    POSITIVE LOGITS
    æĹ¢åı¯ä»¥
    0.11
    ertools
    0.11
    SingleNode
    0.10
    YSTEM
    0.10
    /operator
    0.10
    åľ¨ä¹İ
    0.10
    FRING
    0.10
    jourd
    0.09
    ereum
    0.09
    .datab
    0.09
    Activations Density 1.088%

    No Known Activations