© 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. 38388
    Prev
    Next
    INDEX
    Explanations

    're not, 'll come

    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
    å®ŀåľ¨æĺ¯å¤ª
    -0.09
    çļĦå®ŀéĻħ
    -0.09
    éĩijå±±
    -0.08
    åı¯ä¸įæĺ¯
    -0.08
    æĸĻ
    -0.08
    æĹ¶è¡¨ç¤º
    -0.08
    大å¦Ī
    -0.08
    chio
    -0.08
    iras
    -0.08
    æŶä¸į
    -0.08
    POSITIVE LOGITS
    è¯Ŀè¯Ń
    0.10
    oure
    0.10
     Said
    0.09
    åıįä¹ĭ
    0.09
    éĢıæĺİ
    0.09
     Eg
    0.09
    avan
    0.09
    è±ģ
    0.08
    æĪijèĩªå·±
    0.08
    burg
    0.08
    Activations Density 0.042%

    No Known Activations