© 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. 39617
    Prev
    Next
    INDEX
    Explanations

    causes, health, and 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
    æ»Ķ
    -0.08
    isu
    -0.08
    ikon
    -0.08
    åıįæĢĿ
    -0.08
    ibase
    -0.08
    ÑĪло
    -0.08
    ki
    -0.08
    è´©
    -0.08
    æ·±çŁ¥
    -0.08
    çľĭæĿ¥
    -0.08
    POSITIVE LOGITS
    妨ç¢į
    0.11
    çĶŁæ´»çݯå¢ĥ
    0.11
    ç»IJ
    0.11
    æĭĤ
    0.10
    å¢ŀåĬłäºĨ
    0.10
    åIJİç»Ń
    0.10
    å®īåħ¨éļIJæĤ£
    0.10
    hawk
    0.10
    误导
    0.10
    ä¸Ģ件
    0.10
    Activations Density 0.248%

    No Known Activations