© 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. 35676
    Prev
    Next
    INDEX
    Explanations

    correctness or success

    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
    å«£
    -0.09
    æĹ¢
    -0.09
     trần
    -0.09
    æĶ¹
    -0.09
    swer
    -0.08
     Howe
    -0.08
    æ·±å¤ľ
    -0.08
    ilon
    -0.08
    æĿĤè´¨
    -0.08
    uther
    -0.08
    POSITIVE LOGITS
    åıªè¦ģ
    0.13
    åĩĨ
    0.13
    åıªè¦ģæĺ¯
    0.12
    ä¸į管
    0.11
    ä¸Ģå®ļä¼ļ
    0.10
    æºĸ
    0.10
    æĪIJåĬŁçİĩ
    0.10
    失败
    0.10
    æĢ»ä¼ļ
    0.10
    åıªè¦ģä½ł
    0.10
    Activations Density 0.034%

    No Known Activations