© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36810
    Prev
    Next
    INDEX
    Explanations

    click here for

    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
    æĿŁ
    -0.11
    æľĽ
    -0.10
    ä¸Ĭ线
    -0.09
    ä¸ĵ线
    -0.09
    梳
    -0.09
    çĶļ
    -0.09
    çIJ¢ç£¨
    -0.09
     forthcoming
    -0.09
    ÑİÑģÑĮ
    -0.09
    éĵ¢
    -0.09
    POSITIVE LOGITS
    é¢ĨåĨĽ
    0.09
    akov
    0.09
    çѵ
    0.09
     supposedly
    0.08
     type
    0.08
    ä¸ĵä¸ļåĮĸ
    0.08
     supposed
    0.08
    ç´§
    0.08
    é¼ĵ
    0.08
    _activ
    0.08
    Activations Density 0.007%

    No Known Activations