© 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. 59377
    Prev
    Next
    INDEX
    Explanations

    psychotic disorder symptoms

    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
    æ·±åĪ»çļĦ
    -0.08
    Wy
    -0.08
    _scheme
    -0.08
    æijĨæĶ¾
    -0.08
    é¡¿
    -0.08
    sing
    -0.07
    éĻIJ度
    -0.07
     hills
    -0.07
    emodel
    -0.07
    çĤ¬
    -0.07
    POSITIVE LOGITS
    æĿĢ人
    0.09
    .normal
    0.09
    اÙģÙĬ
    0.09
    cycl
    0.09
    æĿĢäºĨ
    0.09
    mes
    0.09
    ness
    0.09
    æĿĢæīĭ
    0.09
    -leaning
    0.09
    æĪ¢
    0.09
    Activations Density 0.013%

    No Known Activations