© 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. 1667
    Prev
    Next
    INDEX
    Explanations

    end of sentence punctuation

    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
    æĪĸèĢħ说
    -0.09
    å±ģ
    -0.09
    akin
    -0.08
    èĭ´
    -0.08
    Ãło
    -0.08
    iration
    -0.08
    åĪĨæĶ¯æľºæŀĦ
    -0.08
    éŀħ
    -0.08
    ç»Ŀ
    -0.08
    ç½²
    -0.08
    POSITIVE LOGITS
    ä¹Łä¸įæķ¢
    0.10
    éĿ©
    0.09
    ä¸įä¹ħ
    0.09
    æľ¬ç½ij
    0.08
    æľīè¿Ļæł·çļĦ
    0.08
    ä¹Łä¸į
    0.08
    ä¹Łæ²¡æľī
    0.08
    å°ijä¸įäºĨ
    0.08
    åĽłèĢĮ
    0.07
    s
    0.07
    Activations Density 0.292%

    No Known Activations