© 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. 2393
    Prev
    Next
    INDEX
    Explanations

    book titles and authors

    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
    姿
    -0.09
    ìķ¼
    -0.08
    &S
    -0.08
    æł·æľ¬
    -0.08
     declarations
    -0.08
    BAT
    -0.08
    è¿Ħ
    -0.08
    .contents
    -0.08
    ache
    -0.07
     laps
    -0.07
    POSITIVE LOGITS
    è¿Ļæľ¬ä¹¦
    0.13
    ä¸Ģæľ¬
    0.13
    çķħéĶĢ
    0.12
    ä¸Ģæľ¬ä¹¦
    0.11
    ç±į
    0.10
     isbn
    0.10
     book
    0.10
    æļ¢
    0.10
     книги
    0.09
     ì±ħ
    0.09
    Activations Density 0.121%

    No Known Activations