© 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. 38715
    Prev
    Next
    INDEX
    Explanations

    atherosclerosis

    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
    ä¸Ģæľ¬
    -0.10
    åīįè¡Į
    -0.09
    cher
    -0.09
    ä¸Ģæľ¬ä¹¦
    -0.08
    åĽŀéģ¿
    -0.08
    çŃĭ
    -0.08
    浩
    -0.08
    æīĵãģ¡
    -0.08
    åĩ¯
    -0.08
    ä¸ĢæŃ¥
    -0.08
    POSITIVE LOGITS
    theros
    0.10
    ynth
    0.09
    çĨ¹
    0.08
    çĤİ
    0.08
     dul
    0.08
    éĢļè¡Įè¯ģ
    0.08
    使人
    0.08
    èķ
    0.08
    æĸĩåĮĸ建设
    0.08
    é¦Ļèķī
    0.08
    Activations Density 0.232%

    No Known Activations