© 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. 22049
    Prev
    Next
    INDEX
    Explanations

    supervisory control and SCADA systems

    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
    é©®
    -0.10
    é£Ļ
    -0.10
    çĭ¬è§Ĵåħ½
    -0.10
    æĦ¤
    -0.09
    pora
    -0.09
    æħĿ
    -0.08
    imers
    -0.08
    âľª
    -0.08
    çĦ°
    -0.08
    é£
    -0.08
    POSITIVE LOGITS
    æĬ¥èѦ
    0.11
    年产
    0.09
    ç½IJ
    0.09
    å·¥ä¸ļä¼ģä¸ļ
    0.09
    çİ°åľº
    0.09
    åĨ¶éĩij
    0.09
     Boolean
    0.08
    åİĤåĮº
    0.08
    æ°´æ³µ
    0.08
    éĥľ
    0.08
    Activations Density 0.114%

    No Known Activations