© 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. 2488
    Prev
    Next
    INDEX
    Explanations

    car interior and electronics

    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
    åľ¨åºĬä¸Ĭ
    -0.08
    åѵ
    -0.08
    è¦ģä¹Ī
    -0.08
     Quarter
    -0.08
    æ²Ļåıijä¸Ĭ
    -0.08
    åѵåĮĸ
    -0.08
    ç§ģä¸ĭ
    -0.08
    RH
    -0.08
    ration
    -0.07
    æĻ¦
    -0.07
    POSITIVE LOGITS
    ç»
    0.10
    .viewport
    0.10
    ä¾ĭè¡Į
    0.10
    enton
    0.10
    è½®å»ĵ
    0.10
    缺å¸Ń
    0.09
    è¯Ŀ说
    0.09
    éĤ£ä¸Ģ
    0.09
    .Navigate
    0.09
    æĦīæĤ¦
    0.09
    Activations Density 0.054%

    No Known Activations