© 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. 34980
    Prev
    Next
    INDEX
    Explanations

    would be or would want

    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
    Specifier
    -0.10
    ãģĨãģ¡ãģ«
    -0.09
    åĽĽæĸ¹
    -0.09
    åĪ®
    -0.09
    è¿ľæĸ¹
    -0.09
    æŀ«
    -0.08
    éķ¶åµĮ
    -0.08
     Chall
    -0.08
    acey
    -0.08
    ç»ĻåĬĽ
    -0.08
    POSITIVE LOGITS
    ä»»ä½ķä¸Ģ个
    0.10
    éĥ½åºĶ该
    0.10
    ä¹ŁçŁ¥éģĵ
    0.09
    家éĥ½çŁ¥éģĵ
    0.09
     Erect
    0.09
    çļĦä¿¡å¿ĥ
    0.09
    å°±çŁ¥éģĵ
    0.09
    éĥ½åı¯ä»¥
    0.09
     anyone
    0.08
    éĥ½èĥ½å¤Ł
    0.08
    Activations Density 0.035%

    No Known Activations