© 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. 4400
    Prev
    Next
    INDEX
    Explanations

    sense of

    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
    è¿Ļ个ä¸ĸçķĮ
    -0.10
    è¿Ļæľ¬ä¹¦
    -0.09
    èĺ§
    -0.09
    è¿Ļåı¥è¯Ŀ
    -0.09
    æľªç»ı
    -0.08
    æł·çļĦ
    -0.08
    dos
    -0.08
    èĩ»
    -0.08
    æľ¬çĿĢ
    -0.08
    è¿Ļå¼ł
    -0.07
    POSITIVE LOGITS
    /from
    0.11
    osos
    0.10
    è¹Ĭ
    0.10
    lus
    0.10
    æĪ·
    0.09
    akes
    0.09
    istes
    0.08
    entes
    0.08
    ycin
    0.08
    .locals
    0.08
    Activations Density 0.114%

    No Known Activations