© 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. 19110
    Prev
    Next
    INDEX
    Explanations

    time lapsed or passed

    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
    olan
    -0.09
    _CURSOR
    -0.09
    æīĢåľ¨
    -0.09
     Ùĥرة
    -0.09
    æĿ¥çĶµ
    -0.09
    é¾Ļæ¹ĸ
    -0.08
    æħij
    -0.08
    éĹŃ
    -0.08
    lover
    -0.08
    ä¿ĿæĮģçĿĢ
    -0.08
    POSITIVE LOGITS
    æµģéĢĿ
    0.14
    âı³
    0.13
    éĢĿ
    0.12
    å²ģæľĪ
    0.12
    åħīéĺ´
    0.09
    æŶéĹ´åĴĮ
    0.09
    æİī
    0.09
    elapsed
    0.09
    度
    0.09
    æŶåħī
    0.09
    Activations Density 0.060%

    No Known Activations