© 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. 47848
    Prev
    Next
    INDEX
    Explanations

    those who are formerly

    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
    éĤ£æł·çļĦ
    -0.09
    æĪIJçĨŁçļĦ
    -0.09
    éĤ£ç§į
    -0.09
    è¿Ļä¸ªåľ°æĸ¹
    -0.09
     Champions
    -0.09
    ä¸Ģæĸ¹
    -0.09
    è¿ĻéĩĮæĺ¯
    -0.09
    æį®
    -0.08
    atz
    -0.08
    è¿Ļæĺ¯æĪij
    -0.08
    POSITIVE LOGITS
    æĦĨ
    0.09
    æĺĢ
    0.08
    讵
    0.08
    FileManager
    0.08
    ä½łä»¥ä¸º
    0.08
    çĶļä¹Ī
    0.08
    quential
    0.08
    æĥ
    0.08
    æĵĴ
    0.08
    åıĸå¾ĹäºĨ
    0.07
    Activations Density 0.070%

    No Known Activations