© 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. 54647
    Prev
    Next
    INDEX
    Explanations

    all I, all of, all the

    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
    èĶij
    -0.10
    èĢģ人家
    -0.10
    emes
    -0.09
    æĺİæĹ¥
    -0.09
    å¿ĥè·³
    -0.08
     Andreas
    -0.08
    ç®į
    -0.08
    asel
    -0.08
    annels
    -0.08
    .offer
    -0.08
    POSITIVE LOGITS
    è¿ĻçĤ¹
    0.10
    大å¤ļæķ°
    0.09
    lica
    0.09
    è¿Ļéĥ¨åĪĨ
    0.09
    çļĦä¸ĢåĪĩ
    0.09
    ç»Ŀ大å¤ļæķ°
    0.09
    è¿Ļ次
    0.09
    çĶŁæ´»åľ¨
    0.09
    åIJĦè¡ĮåIJĦä¸ļ
    0.09
    çļĦ人éĥ½
    0.08
    Activations Density 0.041%

    No Known Activations