© 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. 2765
    Prev
    Next
    INDEX
    Explanations

    good idea, wise, advisable

    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
    reich
    -0.11
    éŀł
    -0.10
    èµĦæĸĻæĺ¾ç¤º
    -0.09
    åIJĥè¿ĩ
    -0.09
    çıįçıł
    -0.09
    çŁ¥æĥħ
    -0.09
    è¬Ĥ
    -0.09
    æľĢåħ³éĶ®çļĦ
    -0.09
    stick
    -0.09
    æľĢåħ³éĶ®
    -0.09
    POSITIVE LOGITS
    emd
    0.09
    ERIC
    0.08
     Covent
    0.08
    ernel
    0.08
    arem
    0.08
    ndef
    0.08
    ixo
    0.08
    تÙĦ
    0.08
     конÑĤ
    0.08
    èĤł
    0.08
    Activations Density 0.023%

    No Known Activations