© 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. 36286
    Prev
    Next
    INDEX
    Explanations

    secure encryption

    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
    没éĶĻ
    -0.11
    çļĦéĤ£ä¸Ģ
    -0.10
    纤
    -0.10
    庶
    -0.10
    è¿Ī
    -0.09
    伤å¿ĥ
    -0.09
    ä¸įéĢļ
    -0.09
    åĵĴ
    -0.09
     exec
    -0.08
    ç»Ī身
    -0.08
    POSITIVE LOGITS
    IGATION
    0.09
     ger
    0.09
    æľ¬ç½ijç«Ļ
    0.08
    aller
    0.08
    ä¹ŁæĹłæ³ķ
    0.08
     вÑģÑıк
    0.08
    åŃĺåľ¨ä¸Ģå®ļ
    0.08
    portun
    0.08
    RING
    0.08
    etta
    0.08
    Activations Density 0.017%

    No Known Activations