© 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. 31743
    Prev
    Next
    INDEX
    Explanations

    asking for input from others

    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
     Dome
    -0.09
    onal
    -0.08
    æ¡ī
    -0.08
     Jar
    -0.08
    åįķçĭ¬
    -0.07
     Collaboration
    -0.07
    åĭī
    -0.07
     av
    -0.07
    -highlight
    -0.07
     consec
    -0.07
    POSITIVE LOGITS
    大家
    0.14
    ç»ıéªĮåĴĮ
    0.13
    ä¼Ĺ人
    0.13
    çݩ家们
    0.12
    大家ä¸Ģèµ·
    0.12
    å¸ĮæľĽå¤§å®¶
    0.12
    ä½łä»¬
    0.12
    ç»ıéªĮ丰å¯Į
    0.11
    åIJĦä½į
    0.11
    让大家
    0.11
    Activations Density 0.175%

    No Known Activations