© 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. 21858
    Prev
    Next
    INDEX
    Explanations

    ordering a

    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
    串
    -0.10
    串èģĶ
    -0.09
    åݨæĪ¿
    -0.09
    ftware
    -0.09
    æĹ¥åŃIJ
    -0.09
    çĹħåĽł
    -0.09
    éĶ£
    -0.09
    _REGS
    -0.09
    åºĬ
    -0.09
     elevator
    -0.09
    POSITIVE LOGITS
    åı¯æĮģç»Ń
    0.10
    åĪĨå·¥
    0.09
    tings
    0.09
    ä»£è¡¨åĽ¢
    0.09
    Reviewer
    0.09
    ä½İ碳
    0.08
    åŀĤ
    0.08
    หาร
    0.08
    å¼Ģå·¥
    0.08
     ÑĢож
    0.08
    Activations Density 0.173%

    No Known Activations