© 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. 35767
    Prev
    Next
    INDEX
    Explanations

    Ten Commandments, forbidden, symptoms

    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
    itarian
    -0.09
    åĮĸçļĦ
    -0.09
    论
    -0.08
    课
    -0.08
    _ctl
    -0.08
    æŀµ
    -0.08
     james
    -0.08
     cd
    -0.08
    課
    -0.08
    羣
    -0.07
    POSITIVE LOGITS
    ç¥Ģ
    0.10
    çħ¨
    0.10
    æĬ±ä½ı
    0.10
     Fulton
    0.09
     dziaÅĤa
    0.09
    anter
    0.09
    忤
    0.09
    代çIJĨ人
    0.09
    ç¼ĺåĪĨ
    0.09
    å¨ĥå¨ĥ
    0.09
    Activations Density 0.008%

    No Known Activations