© 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. 2947
    Prev
    Next
    INDEX
    Explanations

    side

    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
    æłĩå¿ĹæĢ§
    -0.09
    еÑģÑģ
    -0.09
    è°Į
    -0.09
    è°į
    -0.09
    omi
    -0.09
    便åı¯
    -0.09
    éĿ¶
    -0.08
    zan
    -0.08
    å¸Ķ
    -0.08
    äºĨä¸Ģä¼ļ
    -0.08
    POSITIVE LOGITS
    è¿Ļè¾¹
    0.19
    éĤ£è¾¹
    0.18
    æĸ¹éĿ¢
    0.15
    æĸ¹éĿ¢çļĦ
    0.14
     side
    0.14
    æĸ¹æĸ¹éĿ¢
    0.14
     ÑģÑĤоÑĢонÑĭ
    0.13
    åı¦ä¸Ģè¾¹
    0.13
    ä¸Ģ侧
    0.13
     phÃŃa
    0.12
    Activations Density 0.047%

    No Known Activations