© 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. 39788
    Prev
    Next
    INDEX
    Explanations

    de/del/des/do prefixes/articles

    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
    åıįæŃ£
    -0.09
    æĹ¢èĥ½
    -0.09
    /moment
    -0.08
    豫
    -0.08
    stem
    -0.08
    itative
    -0.08
    秣
    -0.08
    ä¿¡
    -0.08
    侩
    -0.08
    樾
    -0.08
    POSITIVE LOGITS
    æĹłéĻIJ
    0.10
    éĽ¾
    0.10
    æĻļå¹´
    0.10
    ault
    0.09
    æĶ¿åįıå§Ķåijĺ
    0.08
    æĺ¨å¤©
    0.08
     commerce
    0.08
    AIM
    0.08
    å¨ģå°¼æĸ¯äºº
    0.08
     Kir
    0.08
    Activations Density 0.047%

    No Known Activations