© 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. 1400
    Prev
    Next
    INDEX
    Explanations

    porridge, oatmeal, bran

    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
    ymm
    -0.09
    ç°ª
    -0.09
    åı¬
    -0.09
    olume
    -0.08
    èļĢ
    -0.08
     Geb
    -0.08
    礼
    -0.08
    ppy
    -0.08
    ç¡Ŀ
    -0.08
     reopening
    -0.08
    POSITIVE LOGITS
    ç²¥
    0.14
    ç³Ļ
    0.13
    ç²Ł
    0.10
    红èĸ¯
    0.09
    ereal
    0.09
    aches
    0.09
    obook
    0.09
    èĬ¡
    0.09
    CLUDE
    0.09
    èįŁ
    0.09
    Activations Density 0.030%

    No Known Activations