© 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. 7118
    Prev
    Next
    INDEX
    Explanations

    one-stop, one-year, one-to-one

    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
    TTY
    -0.09
    æĥ³è±¡åĬĽ
    -0.09
    é«ĺå³°æľŁ
    -0.09
    енн
    -0.08
    æĿŀ
    -0.08
    ä¸įå°ij人
    -0.08
     кап
    -0.08
    é¦ĸåıij
    -0.08
    ä¸Ŀä¸Ŀ
    -0.08
    ä¼ļ计å¸Ī
    -0.08
    POSITIVE LOGITS
    ãģŀ
    0.08
     thân
    0.08
    åİŁåĪĻä¸Ĭ
    0.08
    åİŁåĪĻ
    0.08
    bn
    0.08
    强大
    0.08
    oft
    0.08
    ythe
    0.08
     chá»ĭu
    0.08
    ánh
    0.07
    Activations Density 0.030%

    No Known Activations