© 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. 10085
    Prev
    Next
    INDEX
    Explanations

    work starting or commencing

    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
    éĻª
    -0.11
     пÑĢодÑĥкÑĤов
    -0.09
    ä¸Ģ头
    -0.09
    .mvp
    -0.08
    è®¤çľŁåŃ¦ä¹ł
    -0.08
    íıIJ
    -0.08
    EventManager
    -0.08
    innen
    -0.08
    à¹ĭ
    -0.08
    ä¸Ģ份
    -0.08
    POSITIVE LOGITS
     done
    0.09
    ãĥ¦ãĥĭ
    0.09
    Done
    0.08
    éĻ¢éĻ¢å£«
    0.08
     Done
    0.08
    ç¯ĵ
    0.08
    æĥ«
    0.08
     Corpus
    0.08
    units
    0.08
    ail
    0.08
    Activations Density 0.039%

    No Known Activations