© 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. 58414
    Prev
    Next
    INDEX
    Explanations

    lighting, illumination, decoration

    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
    æĥ¨
    -0.11
    åĨ·éĿĻ
    -0.10
    åĨ·åĨ·
    -0.10
    é¼ĵ
    -0.10
    æŃ»
    -0.09
    å¾Ī大ç¨ĭ度
    -0.09
    _BUSY
    -0.09
    强硬
    -0.09
    roup
    -0.09
    å±ħ家
    -0.08
    POSITIVE LOGITS
    彩
    0.10
    éľĩæĴ¼
    0.10
    å·¨åŀĭ
    0.09
    æĪĹ
    0.09
    ç»İ
    0.09
    é¢ĸ
    0.09
    çİ°åľº
    0.09
    æľīæľº
    0.08
     hopes
    0.08
    éĩįçİ°
    0.08
    Activations Density 0.085%

    No Known Activations