© 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. 740
    Prev
    Next
    INDEX
    Explanations

    universities and locations

    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
    Negative Logits
    æĹ©æĻļ
    -0.10
    åĩłåĪĨ
    -0.09
    帽
    -0.09
     mage
    -0.08
    éķ¿çĽ¸
    -0.08
    itorio
    -0.08
    管çIJĨä¸Ńå¿ĥ
    -0.08
    oyo
    -0.08
     Harden
    -0.08
    voke
    -0.08
    POSITIVE LOGITS
    å¸ĤéĿ¢ä¸Ĭ
    0.10
    çľģåĨħ
    0.10
    ç¥ĸåĽ½
    0.09
    æ¸ħåįķ
    0.09
    bios
    0.09
    è´´åIJ§
    0.08
    PropTypes
    0.08
    ä¸ĵåĮº
    0.08
    alone
    0.08
    reh
    0.08
    Activations Density 0.009%

    No Known Activations