© 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. 19833
    Prev
    Next
    INDEX
    Explanations

    visiting places

    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
    åİĭå®ŀ
    -0.10
    à¸Ńà¸ļ
    -0.09
    æ¾³
    -0.09
    ä¸Ģæŀļ
    -0.09
    twig
    -0.09
    æıIJéĢŁ
    -0.09
    ä¸įæĺĵ
    -0.08
    ее
    -0.08
    _IB
    -0.08
     Territories
    -0.08
    POSITIVE LOGITS
    åıĤè§Ĥ
    0.13
    游è§Ī
    0.12
    åı¤
    0.12
    çľĭæľĽ
    0.11
    è§Ĥåħī
    0.11
     sights
    0.11
    åı¤åŁİ
    0.10
    èĢĥå¯Ł
    0.10
    åİ»çľĭ
    0.10
    è§Ĥæij©
    0.10
    Activations Density 0.079%

    No Known Activations