© 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. 6884
    Prev
    Next
    INDEX
    Explanations

    guidelines for method or treatment

    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
    绾
    -0.09
    å·¥ä¼ļ
    -0.09
    éļª
    -0.09
    atchet
    -0.09
    åī¥
    -0.09
    ä¸įæŃ¢
    -0.09
    幸ç¦ıæĦŁ
    -0.09
    åħ®
    -0.09
    éĻ©
    -0.09
    _RESOURCES
    -0.09
    POSITIVE LOGITS
    è§ĦèĮĥ
    0.10
     cÆ°
    0.09
    æĸ¹æĸ¹éĿ¢éĿ¢
    0.09
    åIJĦ个æĸ¹éĿ¢
    0.09
    寮
    0.09
     behavior
    0.09
     conduct
    0.09
     comport
    0.09
     Behavior
    0.08
    Procedure
    0.08
    Activations Density 0.162%

    No Known Activations