© 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. 55705
    Prev
    Next
    INDEX
    Explanations

    day and night time

    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
    羡
    -0.09
    æĴŃ
    -0.09
    ç½¢
    -0.09
    FFE
    -0.09
    å¿ĥæĦı
    -0.09
    door
    -0.09
    éĹ³
    -0.09
    ä½ĵè´¨
    -0.09
    _CRITICAL
    -0.09
    trys
    -0.09
    POSITIVE LOGITS
    å¤ľæĻļ
    0.24
    å¤ľéĹ´
    0.23
    å¤ľ
    0.22
    çĻ½å¤©
    0.21
    æĻļä¸Ĭ
    0.20
    é»ijå¤ľ
    0.19
    å¤ľéĩĮ
    0.19
     night
    0.17
    æĺ¼
    0.16
     nighttime
    0.16
    Activations Density 0.090%

    No Known Activations