© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 40186
    Prev
    Next
    INDEX
    Explanations

    opinion column editor

    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
    Negative Logits
    ä¿Ĺ
    -0.09
    ak
    -0.09
    ÑĤÑı
    -0.09
    第ä¸ĢæĿ¡
    -0.09
     Suc
    -0.08
    æ³Ĭ
    -0.08
    ux
    -0.08
     RTP
    -0.08
    èİĵ
    -0.08
    nod
    -0.08
    POSITIVE LOGITS
    ä¸ĵæłı
    0.13
    åij¨åĪĬ
    0.11
    ä¸Ģç¯ĩ
    0.11
    夹
    0.11
    åĪĬçĻ»
    0.10
    åıij表äºĨ
    0.10
    åıij表
    0.10
    主æŨ
    0.10
    ä»ħ代表
    0.10
    æĮŁ
    0.09
    Activations Density 0.056%

    No Known Activations