© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 39958
    Prev
    Next
    INDEX
    Explanations

    diseases and 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
    Not in Any Lists

    No Comments

    Negative Logits
    åħįè´£
    -0.11
    æ³°å±±
    -0.10
    ancell
    -0.09
     Penis
    -0.09
    å¹³éĿĻ
    -0.09
    èį¤
    -0.08
    adiens
    -0.08
    æĿĮ
    -0.08
    tero
    -0.08
     Canter
    -0.08
    POSITIVE LOGITS
    çļ®èĤ¤çĹħ
    0.10
     diseases
    0.10
    ä½Ŀ
    0.09
     disorders
    0.09
     disorder
    0.09
    åŁºæľ¬ä¸Ĭéĥ½
    0.09
     Type
    0.08
     Ca
    0.08
    uth
    0.08
     Fib
    0.08
    Activations Density 0.431%

    No Known Activations