© 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. 37923
    Prev
    Next
    INDEX
    Explanations

    computer or PC

    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
    idy
    -0.11
    srv
    -0.09
    adol
    -0.09
    endor
    -0.09
     Dix
    -0.09
     Ñģобой
    -0.09
    æį»
    -0.09
    èĨij
    -0.09
    iance
    -0.09
    anka
    -0.08
    POSITIVE LOGITS
    åĨĹ
    0.09
    orraine
    0.09
    鬼
    0.09
    ä¸įåĬ¨
    0.09
    年轻人
    0.09
    å±ıå¹ķä¸Ĭ
    0.08
    æĶ¯
    0.08
    ä¸ĬçļĦ
    0.08
    folk
    0.08
    éģĵçIJĨ
    0.08
    Activations Density 0.285%

    No Known Activations