© 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. 51315
    Prev
    Next
    INDEX
    Explanations

    often times

    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
    åıĪæľī
    -0.09
    å§ĭç»Īä¿ĿæĮģ
    -0.09
    åIJIJ槽
    -0.09
    å±ĭéĩĮ
    -0.09
    éĢIJæ¸IJ
    -0.08
    elts
    -0.08
    ä¸įæĸŃå¢ŀåĬł
    -0.08
    å¾ĪæŃ£å¸¸
    -0.08
    æºIJæºIJä¸įæĸŃ
    -0.08
    æĽ´æľī
    -0.08
    POSITIVE LOGITS
    entimes
    0.13
    å¾Ģå¾Ģæĺ¯
    0.12
    æĥħåĨµä¸ĭ
    0.10
    ä¼ļåıijçĶŁ
    0.10
    çĶļèĩ³æĺ¯
    0.09
    cret
    0.09
    æĺ¯ä»İ
    0.09
    ÑĩаÑģÑĤ
    0.09
    ä»ĸ们ä¼ļ
    0.09
    RING
    0.09
    Activations Density 0.050%

    No Known Activations