© 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. 40071
    Prev
    Next
    INDEX
    Explanations

    only person, only game, first clinical

    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
    licas
    -0.09
    anke
    -0.09
    ä¸įæĥľ
    -0.09
    .metamodel
    -0.09
    ÙģÙĪر
    -0.09
    uger
    -0.08
    allen
    -0.08
    Earn
    -0.08
    çīĮ
    -0.08
     Cotton
    -0.08
    POSITIVE LOGITS
    town
    0.09
    çīĪæĿĥæīĢæľī
    0.08
    æĪIJ份
    0.08
    god
    0.08
    è¯ı
    0.08
    9
    0.08
     apprec
    0.08
    çĥĿ
    0.08
    ä¸įèĪĴæľį
    0.08
    ç»ĦæĪIJ
    0.08
    Activations Density 0.026%

    No Known Activations