© 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. 4203
    Prev
    Next
    INDEX
    Explanations

    fusion, otype, metonymic, secular, liberal

    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
    é»ĺ
    -0.10
    æ¶ĵ
    -0.08
    ä¸Ńåħ±
    -0.08
    ä½Ŀ
    -0.08
    åĵ²åѦ
    -0.08
    æ¸ħæ·¡
    -0.08
    称ä¹ĭ
    -0.08
    ä½ľåĵģ
    -0.08
    arius
    -0.08
    é»ĺé»ĺ
    -0.08
    POSITIVE LOGITS
    èĭķ
    0.08
    ä¸įåľ¨
    0.08
    urance
    0.08
     ÑĢаÑģÑĤв
    0.08
    楹
    0.08
    åĿIJæłĩ
    0.08
    æµ·åŁŁ
    0.08
    çļĦç»ıéªĮ
    0.08
     extr
    0.08
    å¼ĤæĢ§
    0.08
    Activations Density 0.098%

    No Known Activations