© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 39156
    Prev
    Next
    INDEX
    Explanations

    documentation generators and sites

    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
    çļĦçłĶåıij
    -0.09
    æĸ°åįİç½ij
    -0.09
    dif
    -0.09
    麾
    -0.08
    åĨ
    -0.08
    çīĽèĤī
    -0.08
    æĵį
    -0.08
    åĨľåī¯äº§åĵģ
    -0.08
    lining
    -0.08
    产åĵģçłĶåıij
    -0.08
    POSITIVE LOGITS
    ä¸Ģ个å¤ļ
    0.09
    inki
    0.09
    curso
    0.09
     furn
    0.08
    pta
    0.08
    roid
    0.08
    ä»Ĭ天çļĦ
    0.08
    íĶ½
    0.08
    ÙĬاÙĨ
    0.08
    çĶ¨æ°´
    0.08
    Activations Density 0.572%

    No Known Activations