© 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. 4233
    Prev
    Next
    INDEX
    Explanations

    quoted words

    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
    enci
    -0.09
    iceps
    -0.08
    2
    -0.08
    æ¯ĶåĪ©
    -0.08
    æļĹ
    -0.08
    ä¹Łä¸įæķ¢
    -0.08
    èĮħ
    -0.08
    羣æŃ£çļĦ
    -0.08
    è£Ķ
    -0.08
    é£ĺ
    -0.08
    POSITIVE LOGITS
    åıĪ称
    0.14
    ä¿Ĺ称
    0.11
    ä¹Łå°±æĺ¯
    0.11
    ableView
    0.10
    éĢļä¿Ĺ
    0.10
    ãģ¨ãģĦãģ£ãģ¦
    0.10
    æĬĬè¿ĻäºĽ
    0.10
    è¿Ļ个è¯į
    0.10
    æĿ¥å½¢å®¹
    0.09
     aka
    0.09
    Activations Density 0.427%

    No Known Activations