© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 50438
    Prev
    Next
    INDEX
    Explanations

    causes medical conditions

    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
    è¿ĺæľīä¸Ģ个
    -0.11
    ï¸
    -0.10
    åģļå¾Ĺ
    -0.10
    è¿ĺæľīå¾Īå¤ļ
    -0.09
    è¿ĺæľī
    -0.09
    ftime
    -0.09
     nature
    -0.09
    hower
    -0.09
    çŁ¥ä¹İ
    -0.09
    ê»Ģ
    -0.09
    POSITIVE LOGITS
    äºĨä¸Ģç³»åĪĹ
    0.13
    ä»Ģä¹Īåij¢
    0.10
    äºĨä¸Ģ
    0.10
    æŀģ大
    0.09
    èĢģ大
    0.09
    æŀģ大çļĦ
    0.09
    ç¿Į
    0.09
    类似äºİ
    0.09
    åĢį
    0.09
    ä¸įäºĨ
    0.09
    Activations Density 0.133%

    No Known Activations