© 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. 21364
    Prev
    Next
    INDEX
    Explanations

    date separator

    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
    eper
    -0.10
    noinspection
    -0.10
    ä¸İåIJ¦
    -0.10
    太å¤ļçļĦ
    -0.10
    ä½Ĩä¸įéĻIJäºİ
    -0.10
    аÑĢÑĮ
    -0.09
    微信åı·
    -0.09
    åĴĮ个人
    -0.09
    æ°¸éģł
    -0.08
    ÑģÑĮ
    -0.08
    POSITIVE LOGITS
    /goto
    0.10
    hl
    0.08
     Happ
    0.08
    starter
    0.08
    pliant
    0.08
    itals
    0.08
    å·¦åı³
    0.08
     ожи
    0.08
    witter
    0.08
    æŃ£æĺ¯
    0.07
    Activations Density 0.123%

    No Known Activations