© 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. 50276
    Prev
    Next
    INDEX
    Explanations

    on the

    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
    _GU
    -0.09
    èĩ³ä¸Ĭ
    -0.08
    emann
    -0.08
    ç¦ıçĶ°
    -0.08
    ActionResult
    -0.08
    å¤ĸæ±ĩ
    -0.08
     ×ŀ×Ļ
    -0.08
    æĹ¶ç©º
    -0.08
    åĢ¡
    -0.08
    /widget
    -0.08
    POSITIVE LOGITS
    æĪ·å¤ĸ
    0.10
     Outdoor
    0.10
    室å¤ĸ
    0.10
    agation
    0.09
    æĪ¶
    0.09
     outdoor
    0.09
    人å¿ĥ
    0.09
    æ»ĭ润
    0.09
    人们çļĦ
    0.09
    пп
    0.08
    Activations Density 0.256%

    No Known Activations