© 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. 56542
    Prev
    Next
    INDEX
    Explanations

    can find

    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
    åĪ¹
    -0.11
    ä¸ĢåłĨ
    -0.09
    æ´»åĬ¨ä¸Ń
    -0.09
    è¹ij
    -0.09
    èļĤ
    -0.08
    课å¤ĸ
    -0.08
    кÑĢа
    -0.08
    imir
    -0.08
    èĭ¦èĭ¦
    -0.08
    éıĸ
    -0.08
    POSITIVE LOGITS
    æĭ¨æīĵ
    0.09
    åľ¨åĵªéĩĮ
    0.09
     blow
    0.09
    rott
    0.09
    é¢Ĩåıĸ
    0.09
    详ç»ĨçļĦ
    0.09
    åħ·ä½ĵçļĦ
    0.08
    åįģäºĮæĿ¡
    0.08
    åĮ¿åIJį
    0.08
    ailable
    0.08
    Activations Density 0.027%

    No Known Activations