© 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. 33489
    Prev
    Next
    INDEX
    Explanations

    broken, cling, revealing, showed

    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
    еÑĢÑĮ
    -0.11
    帰
    -0.10
    éĿŀ常å¤ļçļĦ
    -0.10
    éĥ½æĺ¯éĿŀ常
    -0.10
    åı¯è°ĵæĺ¯
    -0.10
     Cardinals
    -0.09
    è¿ĻäºĽä¸ľè¥¿
    -0.09
    è¿ĻäºĽéĥ½æĺ¯
    -0.09
    è¿Ļæĸ¹éĿ¢
    -0.09
    éĿ´
    -0.09
    POSITIVE LOGITS
    åĩł
    0.09
    çĨŁæĤīçļĦ
    0.09
    ä¼¼ä¹İ
    0.08
    é»Ħ
    0.08
    çĨŁæĤī
    0.08
    åįĬ
    0.08
    æ³ķå®ļ
    0.08
    .pref
    0.08
    æĸ°å¼Ģ
    0.08
    inel
    0.07
    Activations Density 0.189%

    No Known Activations