© 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. 55570
    Prev
    Next
    INDEX
    Explanations

    user-generated content

    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
    åIJ®
    -0.09
    ç¿»
    -0.09
     concession
    -0.09
    çģ¯åħī
    -0.09
    SEC
    -0.09
    æĺ¯éĿŀ
    -0.09
    بÙĪ
    -0.08
    éĢįéģ¥
    -0.08
    _flutter
    -0.08
    umph
    -0.08
    POSITIVE LOGITS
    è¨Ģ论
    0.10
    UGC
    0.10
    çļĦåĨħ容
    0.09
    å¯ĦãģĽ
    0.09
    å¾ģ
    0.09
    ä¸Ģç§Ĵ
    0.09
    ä½ıäºĨ
    0.09
    æĻ¾
    0.08
    浯
    0.08
    submitted
    0.08
    Activations Density 0.009%

    No Known Activations