© 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. 55576
    Prev
    Next
    INDEX
    Explanations

    are followed by descriptors

    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¸ī个
    -0.11
    è¿Ļ两ç§į
    -0.10
    æĺ¯ä¸Ģ件
    -0.10
    主è¦ģæľī
    -0.10
    è¿Ļåĩłä¸ª
    -0.09
    ãģ®ä¸Ģ
    -0.09
    ä¸īä½į
    -0.09
    ä¸īç§į
    -0.09
    æľī两ç§į
    -0.09
    两ç§į
    -0.09
    POSITIVE LOGITS
    ä¹ĭç±»çļĦ
    0.11
    ä¹ĭç±»
    0.10
    太æŀģ
    0.10
    ikt
    0.10
    åĪ«äºº
    0.09
    _radi
    0.09
     ÑĢаÑģÑģмаÑĤÑĢива
    0.09
    ç¿İ
    0.09
    çķĻå®Ī
    0.09
    å©¿
    0.09
    Activations Density 0.207%

    No Known Activations