© 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. 32095
    Prev
    Next
    INDEX
    Explanations

    weather and environmental conditions

    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
    æĶ¯
    -0.10
    è¸Ĭ
    -0.09
    cul
    -0.09
    Ops
    -0.09
    æĿ¥è®²
    -0.09
    æģª
    -0.08
    çªĴæģ¯
    -0.08
    ç¯ij
    -0.08
    èľ»
    -0.08
    侨
    -0.08
    POSITIVE LOGITS
    é£İ鼨
    0.16
    鼨
    0.14
     weather
    0.14
    weather
    0.14
     rain
    0.13
    天æ°Ķ
    0.13
    _weather
    0.12
     Weather
    0.12
    æ·ĭ
    0.12
    Weather
    0.12
    Activations Density 0.064%

    No Known Activations