© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38261
    Prev
    Next
    INDEX
    Explanations

    code comments and file references

    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¸ĢåĪĩ
    -0.09
    ç»¿åľ°
    -0.08
    çļĦåIJĦç§į
    -0.08
    çļĦåIJĦ项
    -0.08
    åIJĦç§į
    -0.08
    åIJĦ项
    -0.08
    ami
    -0.08
    è¿ĺå¾Ĺ
    -0.08
    离ä¸įå¼Ģ
    -0.07
    çī¹æ®ĬæĥħåĨµ
    -0.07
    POSITIVE LOGITS
    çº
    0.10
    好åIJ§
    0.09
    _LAT
    0.09
    ç«ĭæ¡Ī
    0.09
    iek
    0.09
    ombo
    0.09
    訾
    0.09
    éŀħ
    0.09
    æŃ£æĸĩ
    0.09
     Baghd
    0.08
    Activations Density 0.193%

    No Known Activations