© 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. 33746
    Prev
    Next
    INDEX
    Explanations

    sunset and evening

    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
    ä¸į让
    -0.09
    vent
    -0.09
    leck
    -0.09
    碰
    -0.09
     prepaid
    -0.09
    æĹłç¼ĺ
    -0.08
    为é¦ĸçļĦ
    -0.08
    æĬĹè¡¡
    -0.08
    vented
    -0.08
    ä¸Ģç»ı
    -0.08
    POSITIVE LOGITS
     evening
    0.21
    é»Ħæĺı
    0.20
    å¤ķ
    0.19
    å¤ķéĺ³
    0.19
    æĻļä¸Ĭ
    0.18
    åĤįæĻļ
    0.17
    æĻļéĹ´
    0.16
    æĻļ
    0.15
     sunset
    0.15
     evenings
    0.15
    Activations Density 0.060%

    No Known Activations