© 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. 52713
    Prev
    Next
    INDEX
    Explanations

    each of

    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
    ä»»ä½ķå½¢å¼ı
    -0.10
    å¥Ĥ
    -0.09
    æŁIJäºĽ
    -0.08
    使çĶ¨æĿĥ
    -0.08
     Henrik
    -0.08
    马ä¸Ĭ
    -0.08
     winters
    -0.08
     Stuff
    -0.08
     stuff
    -0.08
    åĽ¾çĶ»
    -0.08
    POSITIVE LOGITS
     respective
    0.11
    ä¸Ģ个个
    0.10
    çijĻ
    0.09
    ãģ¾ãģĹãģ¦
    0.09
    terr
    0.09
    亮çĤ¹
    0.09
    ç±»åŀĭçļĦ
    0.09
     lã
    0.09
    æĦıå¢ĥ
    0.09
     конкÑĢеÑĤ
    0.09
    Activations Density 0.045%

    No Known Activations