© 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. 36301
    Prev
    Next
    INDEX
    Explanations

    just the perfect thing

    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
    缴éĶĢ
    -0.08
    常è§ģçļĦ
    -0.08
    ucz
    -0.08
    epam
    -0.08
     monstr
    -0.08
     bol
    -0.08
    ATT
    -0.08
     ded
    -0.08
    Ñĥ
    -0.08
     Serving
    -0.08
    POSITIVE LOGITS
    æŃ£å¥½
    0.13
    æģ°å¥½
    0.12
    åIJĪéĢĤ
    0.11
    åIJĪéĢĤçļĦ
    0.11
    æģ°æģ°
    0.10
    éĿŀ常éĢĤåIJĪ
    0.10
     perfectly
    0.10
    æ¦ĤåĨµ
    0.10
     Bened
    0.09
    ä¸Ģåī¯
    0.09
    Activations Density 0.077%

    No Known Activations