© 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. 56407
    Prev
    Next
    INDEX
    Explanations

    be sure to check out

    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
    åįķä¸Ģ
    -0.09
    åIJĦçķĮ
    -0.09
    åĢı
    -0.09
    çŃ®
    -0.09
    æĪĸå°Ĩ
    -0.09
    æ¦ĤåĨµ
    -0.08
    è¿Ħä»Ĭ
    -0.08
    åij¸
    -0.08
    æīĢæıIJä¾ĽçļĦ
    -0.08
    æĪĸ许
    -0.08
    POSITIVE LOGITS
    è®°å¾Ĺ
    0.13
    è¨ĺå¾Ĺ
    0.10
    _asc
    0.10
    çķĻæĦı
    0.10
    allen
    0.10
    å¼ĭ
    0.10
    è®°ä½ı
    0.09
    GPL
    0.09
    è°¨
    0.09
    _STRIP
    0.09
    Activations Density 0.007%

    No Known Activations