© 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. 1952
    Prev
    Next
    INDEX
    Explanations

    soluble proteins

    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
    âľİ
    -0.09
    ä½İ温
    -0.08
    ollah
    -0.08
    çĩ¥
    -0.08
    ç¢
    -0.08
    大楼
    -0.08
    çļĦæĥħæĦŁ
    -0.08
    æĻ®éĢļ
    -0.08
    åĬłä¸Ĭ
    -0.08
    åľ°éĿ¢
    -0.08
    POSITIVE LOGITS
    éĻĦ
    0.09
    æĽ´éĩįè¦ģçļĦ
    0.09
     Nurs
    0.09
    èĻ¹
    0.09
     Colomb
    0.09
    éĢ¸
    0.09
    財
    0.09
    (SE
    0.09
     Versions
    0.08
    æŶä¸įæŶ
    0.08
    Activations Density 1.351%

    No Known Activations