© 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. 57520
    Prev
    Next
    INDEX
    Explanations

    preset templates

    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
    rios
    -0.10
    驹
    -0.09
    羣æŃ£çļĦ
    -0.09
     programm
    -0.09
    FAST
    -0.09
    çĽ¸å¯¹è¾ĥ
    -0.09
    æĸĩä¸Ń
    -0.08
    ÑĥÑĪ
    -0.08
    owie
    -0.08
    _handling
    -0.08
    POSITIVE LOGITS
    åı¯ä¾Ľ
    0.12
    模æĿ¿
    0.11
    åºĵ
    0.11
     templates
    0.10
    ç´ł
    0.10
    ç´łæĿIJ
    0.10
    丰å¯Į
    0.10
    æłĩåĩĨ
    0.10
    éĢĤçĶ¨äºİ
    0.09
    æ¯ĽåŃĶ
    0.09
    Activations Density 0.215%

    No Known Activations