© 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. 23209
    Prev
    Next
    INDEX
    Explanations

    interested in/to/mainly

    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
     ÑĥÑģили
    -0.10
    .between
    -0.09
    /or
    -0.09
    çĭĤ
    -0.09
    coe
    -0.09
    (Mod
    -0.08
    æĿ¥èĩª
    -0.08
    ende
    -0.08
    åĩºèĩª
    -0.08
    å¯ĦãģĽ
    -0.08
    POSITIVE LOGITS
    ä¹Łä¸įæĥ³
    0.14
    æļĩ
    0.10
    çļĦä¸ľè¥¿
    0.10
    è¦ģ好好
    0.10
    çļĦæĺ¯
    0.10
    ubar
    0.09
    æĺİæĹ¥
    0.09
    echa
    0.09
    çļĦå°±æĺ¯
    0.09
    ä½ŀ
    0.09
    Activations Density 0.021%

    No Known Activations