© 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. 47565
    Prev
    Next
    INDEX
    Explanations

    mental health disorders

    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
    emme
    -0.09
    eer
    -0.09
     кÑĢови
    -0.08
    yı
    -0.08
    alone
    -0.08
    events
    -0.08
    ÑĩаÑĤ
    -0.08
    æĸ½èĤ¥
    -0.08
    à¸ĺรรม
    -0.08
    skin
    -0.08
    POSITIVE LOGITS
    istic
    0.11
    çĿ¬
    0.10
    ually
    0.09
    licity
    0.09
    umbed
    0.09
    ioned
    0.09
    wares
    0.09
    idade
    0.09
    icans
    0.09
    å±ĭ
    0.08
    Activations Density 0.014%

    No Known Activations