© 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. 19086
    Prev
    Next
    INDEX
    Explanations

    code symbols and tab

    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
    å¾Ģäºĭ
    -0.09
    ä»Ĭãģ¯
    -0.09
    æĢ¿
    -0.08
    å¿Ĺ强
    -0.08
    éĵĽ
    -0.08
    èij³
    -0.08
    ç«ŀäºī对æīĭ
    -0.08
    éĴº
    -0.08
    åIJĮæĻĤãģ«
    -0.08
    ivered
    -0.08
    POSITIVE LOGITS
    ãģŁãĤģãģ«
    0.11
    åIJĦç§į
    0.11
    äºĽ
    0.10
    人éĥ½
    0.10
    æł¹æľ¬
    0.10
    ç¾İ好
    0.10
    åľ°åĿª
    0.10
    æľĢ大
    0.09
    åľŁåľ°
    0.09
    çľĭæ³ķ
    0.09
    Activations Density 0.358%

    No Known Activations