© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 812
    Prev
    Next
    INDEX
    Explanations

    time ranges

    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
    Negative Logits
    æģ°å½ĵ
    -0.08
    ä¸Ģç»ı
    -0.08
    åĴĮåıijå±ķ
    -0.08
    飬
    -0.08
    æĹ©å°±
    -0.08
    èĥ½åĬĽåĴĮ
    -0.08
    ä½ĵçİ°åľ¨
    -0.08
    æĹ©æľŁ
    -0.08
    æĹ©æĻ¨
    -0.08
    angu
    -0.08
    POSITIVE LOGITS
    为æŃ¢
    0.16
    åĨįåĪ°
    0.13
    寻
    0.12
    phans
    0.11
     ÙĪØŃتÙī
    0.11
    ä¸ĭ鼨
    0.10
    缴èĩ³
    0.10
    å¯Įæ°ij
    0.10
    clusive
    0.09
    rouch
    0.09
    Activations Density 0.088%

    No Known Activations