© 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. 3889
    Prev
    Next
    INDEX
    Explanations

    brain injury severity

    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
    æĺ¯ä»İ
    -0.10
    横åIJij
    -0.09
    å¾ĹæĦı
    -0.09
    çĻĸ
    -0.09
    åİĨ代
    -0.08
    æīĵæ³ķ
    -0.08
    ä»İæĿ¥
    -0.08
    éªĦåĤ²
    -0.08
    ORED
    -0.08
    åĸľ
    -0.08
    POSITIVE LOGITS
    éļ§
    0.10
    éĨĴ
    0.10
    寸
    0.09
    鹫
    0.09
    è§īéĨĴ
    0.09
    转åħ¥
    0.09
    éĨĴäºĨ
    0.09
    æķ¬
    0.08
    äºĮ人
    0.08
    ä¸ĩ亿
    0.08
    Activations Density 0.254%

    No Known Activations