© 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. 7545
    Prev
    Next
    INDEX
    Explanations

    how to help or use something

    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
    对èĩªå·±çļĦ
    -0.09
    æī£
    -0.09
    åıijçİ°èĩªå·±
    -0.08
    åĬ¢
    -0.08
     styles
    -0.08
    åľ¨å¹¿å·ŀ
    -0.08
    ä¸İåħ¶ä»ĸ
    -0.08
    Visit
    -0.08
    ä¸įå¿ħè¦ģçļĦ
    -0.08
     Visit
    -0.08
    POSITIVE LOGITS
    abinet
    0.10
    åĩĨ
    0.09
    permission
    0.09
    éħįæľī
    0.09
    rieg
    0.09
    æľĢç¾İ
    0.09
     пÑģ
    0.09
    squeeze
    0.09
    kaar
    0.09
    nest
    0.09
    Activations Density 0.001%

    No Known Activations