© 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. 4583
    Prev
    Next
    INDEX
    Explanations

    if I were

    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
    ä¸įåĩĨ
    -0.09
     cof
    -0.09
    æıı
    -0.08
    并ä¸įèĥ½
    -0.08
    tems
    -0.08
    ivy
    -0.08
    holm
    -0.08
    缮
    -0.08
    _already
    -0.08
    å®ŀéĻħä¸Ĭæĺ¯
    -0.08
    POSITIVE LOGITS
    æľīéĴ±
    0.10
    åĨįæĿ¥
    0.10
    笺
    0.10
    å¯ĵ
    0.10
    iez
    0.10
    ãģĦãģŁãĤī
    0.10
    æľīæľºä¼ļ
    0.10
    åı¯ä»¥éĢīæĭ©
    0.09
    ä¼ļéĢīæĭ©
    0.09
    éĻIJ
    0.09
    Activations Density 0.021%

    No Known Activations