© 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. 54555
    Prev
    Next
    INDEX
    Explanations

    to be

    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
    reds
    -0.09
    éĢĤ度
    -0.09
    å¼Ħ
    -0.08
    è¶ģ
    -0.08
    æĽ´å¿«
    -0.08
    举é£İ
    -0.08
    è¢Ĥ
    -0.08
    æĽ´å¤ļä¿¡æģ¯
    -0.08
     Hend
    -0.08
    .multipart
    -0.08
    POSITIVE LOGITS
    åİī害
    0.13
    å¤ļåľ°
    0.12
    å¤ļä¹Ī
    0.11
    éģ¥è¿ľ
    0.10
    大çļĦ
    0.10
    éĨĴ缮
    0.10
    å°ijè§ģ
    0.10
    еÑģÑĮ
    0.10
    容æĺĵ
    0.10
    é£ĺ
    0.10
    Activations Density 0.140%

    No Known Activations