© 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. 34497
    Prev
    Next
    INDEX
    Explanations

    neuropsychological functioning and impairments

    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
    æļĹ
    -0.09
     Baxter
    -0.09
    åŃ£
    -0.08
    çģĮ
    -0.08
    æľµ
    -0.08
    æĹłçŁ¥
    -0.08
    åĩºéģĵ
    -0.08
    RS
    -0.08
    hest
    -0.08
     Greenwood
    -0.08
    POSITIVE LOGITS
    æ·±åĬłå·¥
    0.10
    æ©«
    0.09
    _capability
    0.09
    motor
    0.09
    åĨĽå·¥
    0.09
    æĸ°éĹ»ç½ij
    0.09
    æĭ¼éŁ³
    0.09
    èĥ½åĬĽåĴĮ
    0.09
    ocop
    0.09
    æĮ¹
    0.09
    Activations Density 0.380%

    No Known Activations