© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19921
    Prev
    Next
    INDEX
    Explanations

    probablylikely

    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
    个åĪ«
    -0.10
    请大家
    -0.08
    被认为
    -0.08
    æŁĿ
    -0.08
    oom
    -0.08
     curso
    -0.08
    ToObject
    -0.08
    ä¸į妨
    -0.08
     Rum
    -0.08
    ow
    -0.08
    POSITIVE LOGITS
    æĪĸå¤ļæĪĸå°ij
    0.13
    åľ¨æĦı
    0.10
     already
    0.10
    å·²ç»ıåľ¨
    0.10
    ãģĻãģ§ãģ«
    0.10
    å·²ç»ıæľī
    0.09
    è¿Ļå¥Ĺ
    0.09
    ä½łä¹Ł
    0.09
    ä¹ŁçŁ¥éģĵ
    0.09
    ç¼Ł
    0.09
    Activations Density 0.063%

    No Known Activations