© 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. 27132
    Prev
    Next
    INDEX
    Explanations

    German/European place names

    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
    çĵĴ
    -0.09
    è¿ĻæĶ¯
    -0.09
    ä¹īä¹Į
    -0.08
    辦æ³ķ
    -0.08
    éĢ¡
    -0.08
     Bloody
    -0.08
    ä¹īåĬ¡
    -0.08
    æijĩ
    -0.08
    äºļ马
    -0.08
    ä¸ĢæĶ¯
    -0.08
    POSITIVE LOGITS
    åªĴ
    0.11
    åĿĢ
    0.10
    ä¼Ļ
    0.10
    åįĪé¤IJ
    0.09
    å¤Ķ
    0.09
    rie
    0.09
    æŃ£å¸¸ä½¿çĶ¨
    0.09
    æ¬ºè´Ł
    0.09
    欺
    0.09
    é«ĺéĢŁåħ¬è·¯
    0.09
    Activations Density 0.076%

    No Known Activations