© 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. 29525
    Prev
    Next
    INDEX
    Explanations

    oscope

    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
    CodeGen
    -0.08
    /respond
    -0.08
    atsby
    -0.08
    ves
    -0.08
    umbing
    -0.08
    æĺİæľĿ
    -0.07
    ters
    -0.07
    èij£
    -0.07
    eming
    -0.07
    ZA
    -0.07
    POSITIVE LOGITS
    oft
    0.11
    åħ¨ä½ĵåijĺå·¥
    0.10
    ä¸ļä½Ļ
    0.10
    testdata
    0.10
    åīįä»»
    0.10
    çı£
    0.09
    ä¸ĩåĪĨ
    0.09
    çıŃ车
    0.09
     Barrel
    0.09
    缤纷
    0.09
    Activations Density 0.001%

    No Known Activations