© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7468
    Prev
    Next
    INDEX
    Explanations

    after a certain point

    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
    è¾Ĥ
    -0.09
    è´¢ç»ı
    -0.09
    黳
    -0.08
    红楼
    -0.08
    好åĥıæĺ¯
    -0.08
    æ¯ĵ
    -0.08
    åħĪçĶŁ
    -0.08
    æĪij说
    -0.07
    èĵĬ
    -0.07
    èĭ¥å¹²
    -0.07
    POSITIVE LOGITS
    å®ŀåĬĽ
    0.11
    çļĦå®ŀåĬĽ
    0.10
    å¹²æ¶ī
    0.10
    igne
    0.10
    伤亡
    0.09
    æĪĺæĸĹ
    0.09
    渺
    0.09
    _PRIMARY
    0.08
    æĥħæĬ¥
    0.08
    ultz
    0.08
    Activations Density 0.231%

    No Known Activations