© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 26159
    Prev
    Next
    INDEX
    Explanations

    center of

    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
    Negative Logits
     Kron
    -0.10
    sing
    -0.09
    oine
    -0.08
    ØŃÙĤ
    -0.08
    erus
    -0.08
    иÑĤел
    -0.08
     plastics
    -0.08
     Lev
    -0.08
    rous
    -0.08
    ëŀij
    -0.07
    POSITIVE LOGITS
    /right
    0.10
    èĪĨ论
    0.10
    æ·±æ¸Ĭ
    0.09
    ç
    0.09
    æĹ¢è¦ģ
    0.09
    (formatter
    0.09
    éĺ²çº¿
    0.09
    OSP
    0.09
    ENDOR
    0.09
    ä¸Ģ群
    0.09
    Activations Density 0.020%

    No Known Activations