© 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. 34151
    Prev
    Next
    INDEX
    Explanations

    making something better

    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
    åįĩ
    -0.10
     Rena
    -0.09
    æĭĵ
    -0.09
    çħ§
    -0.08
    ä»ĸ表示
    -0.08
    ones
    -0.08
    ä¼Łå¤§çļĦ
    -0.08
     ìĭ
    -0.08
     beaut
    -0.08
    è°©
    -0.08
    POSITIVE LOGITS
    äº§åľ°
    0.09
    åı¯è§Ĩ
    0.09
    æĭŃ
    0.09
    ä½Ľæ³ķ
    0.08
    åı¯æĥ³
    0.08
    è¿Ļæīįæĺ¯
    0.08
    éĩijå±±
    0.08
    æ¯ı天éĥ½
    0.08
    è¿ĩéĶĻ
    0.08
    зд
    0.08
    Activations Density 0.044%

    No Known Activations