© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37992
    Prev
    Next
    INDEX
    Explanations

    compiler/interpreter contrast

    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
    ä½
    -0.09
    åį´ä¸į
    -0.09
    åĪĻæĺ¯
    -0.09
    ä¼ģä¸ļåĴĮ
    -0.09
    ymi
    -0.09
    ä¹Łåıªæľī
    -0.09
    eph
    -0.08
     же
    -0.08
     atleast
    -0.08
    å¥
    -0.08
    POSITIVE LOGITS
     alike
    0.12
    缸ç»ĵåIJĪ
    0.11
    äºĮèĢħ
    0.10
    两ç§į
    0.10
    éĥ½éĿŀ常
    0.09
    è¿Ļ两ç§į
    0.09
    åIJĦæľī
    0.09
    è¿Ļ对
    0.09
    åīįèĢħ
    0.09
    éĥ½å¾Ī
    0.09
    Activations Density 0.446%

    No Known Activations