© 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. 11640
    Prev
    Next
    INDEX
    Explanations

    evening and night times

    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
    éĻ¤å¤ķ
    -0.11
     pri
    -0.09
    åįĬå¤ľ
    -0.09
    æ·±å¤ľ
    -0.08
     overnight
    -0.08
    èĢģåħµ
    -0.08
    æĺ¼
    -0.08
     ноÑĩÑĮ
    -0.08
    å¤ľéĩĮ
    -0.08
    èµį
    -0.08
    POSITIVE LOGITS
    ivot
    0.10
    tap
    0.10
    å±¹
    0.09
    çĶŁäº§è½¦éĹ´
    0.09
    вин
    0.09
    foil
    0.09
    ä¸Ģèĩ´
    0.09
    .permission
    0.09
     Invent
    0.08
    æİĴæĸ¥
    0.08
    Activations Density 0.040%

    No Known Activations