© 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. 2212
    Prev
    Next
    INDEX
    Explanations

    ask yourself why

    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
     Mayer
    -0.10
    èĭ
    -0.10
    èĤ
    -0.09
    rolled
    -0.09
    åıĺåİĭåĻ¨
    -0.09
    交ä¼ļ
    -0.09
     Fay
    -0.08
    imers
    -0.08
    verified
    -0.08
     Ñĩа
    -0.08
    POSITIVE LOGITS
    èĩªå·±çļĦ
    0.10
    å°Ĩèĩªå·±çļĦ
    0.10
     whether
    0.09
     Yourself
    0.09
    身边çļĦ
    0.09
    ä¸Ģä¸ĭ
    0.08
    åĽ½å®¶æĪĺçķ¥
    0.08
    æļĤç¼ĵ
    0.08
    èĩªåĪĨãģĮ
    0.08
    è´¨
    0.08
    Activations Density 0.024%

    No Known Activations