© 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. 7440
    Prev
    Next
    INDEX
    Explanations

    begins with

    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
    缴æĴŃéĹ´
    -0.10
    çĿļ
    -0.10
    说æĺ¯
    -0.09
    ulla
    -0.09
    liv
    -0.09
    ä¸ĢéĶ®
    -0.09
    æĸĩä¸Ń
    -0.09
    udeau
    -0.09
    åIJİåĨį
    -0.09
    å¹´é¾Ħ段
    -0.09
    POSITIVE LOGITS
    è¿ĺæĺ¯è¦ģ
    0.08
    ä¿Ń
    0.08
    æŁĶ
    0.08
    çĿĢçľ¼äºİ
    0.08
     announcement
    0.08
    éĤ£åıª
    0.07
    çĭĤ
    0.07
    å§Ĩ
    0.07
    announcement
    0.07
    Sal
    0.07
    Activations Density 0.032%

    No Known Activations