© 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. 17850
    Prev
    Next
    INDEX
    Explanations

    information call

    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
    æĪijçļĦå¿ĥ
    -0.10
    é¹Ĭ
    -0.09
     caval
    -0.08
    atura
    -0.08
    帮ä»ĸ
    -0.08
    serter
    -0.08
    dorf
    -0.07
    åİļ
    -0.07
    æĪĴ
    -0.07
    ç²¾åįİ
    -0.07
    POSITIVE LOGITS
    èģĶç³»çĶµè¯Ŀ
    0.13
    çĶµè¯Ŀ
    0.12
    æīĵåIJ¬
    0.11
    æµĶ
    0.10
     Weiner
    0.10
    该éĻ¢
    0.10
    isan
    0.09
    oppers
    0.09
    -www
    0.09
    ä¼ģ
    0.09
    Activations Density 0.009%

    No Known Activations