© 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. 21934
    Prev
    Next
    INDEX
    Explanations

    plant varieties

    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
     ÄijÃŃch
    -0.10
    _vi
    -0.09
    è¯Ħå®ļ
    -0.08
    交éĢļäºĭæķħ
    -0.08
    æİĮ
    -0.08
    èģĶ
    -0.08
    èĢĥè¯Ħ
    -0.08
    çĵ¦
    -0.08
    æĴIJ
    -0.08
    å½¢
    -0.08
    POSITIVE LOGITS
    èĦ²
    0.09
    åıªå¾Ĺ
    0.09
    ç´§å¼ł
    0.08
     Hell
    0.08
    æĸ°åĨł
    0.08
    éĻIJéĩı
    0.08
    çĿ¨
    0.08
    欲
    0.08
    olly
    0.08
    plib
    0.08
    Activations Density 0.001%

    No Known Activations