© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9371
    Prev
    Next
    INDEX
    Explanations

    photography sessions

    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
    éľ²
    -0.10
    åĮ¿åIJį
    -0.09
     Spotlight
    -0.09
    \Abstract
    -0.09
    éľ²åĩº
    -0.09
    å±ķè§Ī
    -0.08
    åİŁåŀĭ
    -0.08
    è¿IJè´¹
    -0.08
    被åĬ¨
    -0.08
     anonymous
    -0.08
    POSITIVE LOGITS
    å¥Ĺé¤IJ
    0.10
    ç©¿æ¢Ń
    0.09
    è¿ĩå¾Ģ
    0.09
    ç»ıéªĮåĴĮ
    0.09
    æĸ°äºº
    0.09
    贵宾
    0.09
    æĸĩåĮĸåĴĮ
    0.08
    å¿ħä¸įåı¯
    0.08
    ä¸ĭè¡Į
    0.08
    åĪĨåĮĸ
    0.08
    Activations Density 0.022%

    No Known Activations