© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 970
    Prev
    Next
    INDEX
    Explanations

    certified for publication

    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
    çĿĩ
    -0.09
    æıŃ
    -0.09
     XCT
    -0.09
    鸳
    -0.09
    æģ¨
    -0.09
    弦
    -0.08
    身ä½ĵåģ¥åº·
    -0.08
    pto
    -0.08
    rides
    -0.08
    emics
    -0.08
    POSITIVE LOGITS
    人éĢī
    0.10
    andler
    0.09
    豪
    0.09
    éĴį
    0.08
    anka
    0.08
     questions
    0.08
    æıIJ款
    0.08
    eg
    0.08
    æĭ¿åĩºæĿ¥
    0.08
    äºĨ解åĪ°
    0.08
    Activations Density 0.336%

    No Known Activations