© 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. 63050
    Prev
    Next
    INDEX
    Explanations

    scientific paper citations

    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
    æĹ©åľ¨
    -0.10
    çļĦä¸Ģ大
    -0.09
    ละ
    -0.08
    就好
    -0.08
    å¤ļå¹´
    -0.08
    0
    -0.08
    bare
    -0.08
     дог
    -0.08
    è¿ĩåIJİ
    -0.08
    .glob
    -0.08
    POSITIVE LOGITS
    ç¬ijè¯Ŀ
    0.10
    ãĢĮ
    0.09
    éĶ¦ç»£
    0.09
    äºıæįŁ
    0.09
    åIJį为
    0.08
    igest
    0.08
    elu
    0.08
    æ¸ħåĩĢ
    0.08
    äºĨä¸Ģç³»åĪĹ
    0.08
    æĥ³èµ·æĿ¥
    0.08
    Activations Density 0.086%

    No Known Activations