© 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. 38931
    Prev
    Next
    INDEX
    Explanations

    to have

    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
    åĿİåĿ·
    -0.11
     ведÑĮ
    -0.10
    鸱
    -0.10
    欹
    -0.10
    .jet
    -0.10
    æħµ
    -0.10
    åºĶ该æĢİä¹Ī
    -0.10
    å¾Ģå¾Ģä¼ļ
    -0.10
    ç»ĻäºĨæĪij
    -0.09
    ä¼ļéķ¿
    -0.09
    POSITIVE LOGITS
    åŃIJéĩĮ
    0.08
     sex
    0.08
    å½ĵåģļ
    0.08
    说åĩºæĿ¥
    0.08
    erview
    0.08
    çī¢åĽº
    0.08
    éĢĤåIJĪèĩªå·±
    0.08
    ties
    0.08
    vinc
    0.07
    åŃIJ
    0.07
    Activations Density 0.032%

    No Known Activations