© 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. 3858
    Prev
    Next
    INDEX
    Explanations

    history of

    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
    èŁĴ
    -0.13
    媵
    -0.09
    åĩºæĿ¥
    -0.09
    é¢Ĩ导èĢħ
    -0.09
    åIJĦè¡Į
    -0.09
    ç§Ģ
    -0.09
    ç»Łè®¡å±Ģ
    -0.08
    edBy
    -0.08
    å³Ħ
    -0.08
    åĩºæĿ¥çļĦ
    -0.08
    POSITIVE LOGITS
    ä¸įæĩĪ
    0.09
    lund
    0.09
    دب
    0.09
     ÑĢазвиÑĤиÑı
    0.09
    æĤłä¹ħ
    0.09
    èĩ³äºİ
    0.09
    æ¼Ķåıĺ
    0.09
    ä¹Łå°±æĺ¯
    0.08
    ä¸ĩ
    0.08
    è¦ģä¸įçĦ¶
    0.08
    Activations Density 0.092%

    No Known Activations