© 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. 7774
    Prev
    Next
    INDEX
    Explanations

    critical thinking and analysis

    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
    pery
    -0.10
    æ¹¾
    -0.10
    ToStr
    -0.09
    èĢIJ
    -0.09
    è´¢çī©
    -0.09
    æĪ¿
    -0.09
    èįĥ
    -0.09
     tanı
    -0.08
    çģ£
    -0.08
    ngo
    -0.08
    POSITIVE LOGITS
    æĢĿèĢĥ
    0.09
     critically
    0.09
     Gim
    0.09
    åĪ³
    0.09
    çĽ¸ä¼´
    0.09
    /latest
    0.09
    иÑĢÑĥеÑĤÑģÑı
    0.08
    èĴĻ
    0.08
    çģ«èĬ±
    0.08
    imon
    0.08
    Activations Density 0.020%

    No Known Activations