© 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. 34817
    Prev
    Next
    INDEX
    Explanations

    all of this is

    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
    è¿Ļä¸Ģ
    -0.12
    è¿Ļæĸ¹éĿ¢
    -0.10
     بذÙĦÙĥ
    -0.10
    éĢĻä¸Ģ
    -0.10
    åľ¨è¿Ļæĸ¹éĿ¢
    -0.10
    Forever
    -0.09
    éĤ£ä¸Ģ
    -0.09
    è¿Ļç§įæĸ¹æ³ķ
    -0.09
    oden
    -0.09
    è¿Ļ项
    -0.09
    POSITIVE LOGITS
    绣绣
    0.11
    éĥ½æ²¡æľī
    0.10
    è¿ĻäºĽéĥ½æĺ¯
    0.10
    麾
    0.09
    éĥ½éľĢè¦ģ
    0.09
    çIJIJ
    0.09
    éĥ½æĺ¯éĿŀ常
    0.09
    ç¾Į
    0.09
    äºĨä¸Ģéģį
    0.09
    idge
    0.09
    Activations Density 0.080%

    No Known Activations