© 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. 54946
    Prev
    Next
    INDEX
    Explanations

    best movie scripts ever

    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
     Redistribution
    -0.10
    Powered
    -0.10
    .Broadcast
    -0.09
     дол
    -0.09
    çļĦæ°Ķæģ¯
    -0.09
    åįı
    -0.09
     ÑĦай
    -0.09
     اÙĦأس
    -0.09
    æĭ¬
    -0.09
    派驻
    -0.08
    POSITIVE LOGITS
    ç»ĵå°¾
    0.11
    æĪĽ
    0.10
    åĽ½éĻħåIJĪä½ľ
    0.09
    åĹ½
    0.09
    循çݯ
    0.09
    è¿Ļç§įæĸ¹å¼ı
    0.08
     finale
    0.08
    è£ħ
    0.08
    æľīå¤ļ
    0.08
    æĸŃè£Ĥ
    0.08
    Activations Density 0.041%

    No Known Activations