© 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. 55667
    Prev
    Next
    INDEX
    Explanations

    details and information

    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
    硼
    -0.11
    æĸ¤
    -0.11
    ä¸įéĢĤ
    -0.09
    å¿«æĿ¥
    -0.09
    ä¿Ŀå®Ī
    -0.09
    ä¸ĢäºĮ
    -0.09
    è£Ļ
    -0.09
    å¯Į豪
    -0.08
    èĦ±èIJ½
    -0.08
     Kaplan
    -0.08
    POSITIVE LOGITS
    çļĦæĹ¥åŃIJéĩĮ
    0.09
    åĴĮæľįåĬ¡
    0.09
    ANO
    0.08
    avic
    0.08
    ä»Ķç»Ĩ
    0.08
    éĿ©
    0.08
    ysz
    0.08
    ĶåĽŀ
    0.08
    çĪ±å¥ĩ
    0.08
     Heller
    0.08
    Activations Density 0.034%

    No Known Activations