© 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. 52927
    Prev
    Next
    INDEX
    Explanations

    that's why

    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
    åı¯çĶ¨
    -0.10
    roc
    -0.09
    åħĪæĺ¯
    -0.09
    æľ¬ç½ij
    -0.09
    ç³ł
    -0.08
    çĵ¢
    -0.08
    ç§ijæĬĢèĤ¡ä»½
    -0.08
    庵
    -0.08
    lux
    -0.08
    åģļçļĦäºĭæĥħ
    -0.08
    POSITIVE LOGITS
    为ä»Ģä¹Ī
    0.19
     why
    0.19
    éļ¾æĢª
    0.15
    çĤºä»Ģ麼
    0.15
     reason
    0.15
    why
    0.15
    为åķ¥
    0.15
     поÑĩемÑĥ
    0.14
    æķħ
    0.14
    æīĢ以æĪij
    0.13
    Activations Density 0.047%

    No Known Activations