© 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. 16952
    Prev
    Next
    INDEX
    Explanations

    brain and spinal cord injury or 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
     Growth
    -0.09
    å¼ĢèĬ±
    -0.09
    颦
    -0.09
    éºĭ
    -0.09
    èįĥ
    -0.09
    èķĥ
    -0.09
    æĬ½æ£Ģ
    -0.09
    vig
    -0.09
    éĹ´è·Ŀ
    -0.08
    pret
    -0.08
    POSITIVE LOGITS
    æ¯ģ
    0.10
    åĮ¡
    0.10
    æįŁåĿı
    0.09
    龸éģĵ
    0.09
    车祸
    0.09
    åĴĦ
    0.09
    伤
    0.08
    å¾Ĺ罪
    0.08
    å®Ŀè´Ŀ
    0.08
    aan
    0.08
    Activations Density 0.245%

    No Known Activations