© 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. 62318
    Prev
    Next
    INDEX
    Explanations

    Lodi, Copic, Jodi, Hood, Hills

    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
    é¾Ļæ³ī
    -0.10
    ero
    -0.09
    æ¶Īè´¹éľĢæ±Ĥ
    -0.09
    æĪIJåĬŁçİĩ
    -0.09
    .jupiter
    -0.09
    ç©¿æ¢Ń
    -0.09
    EXPECT
    -0.08
    绡
    -0.08
    lien
    -0.08
    leys
    -0.08
    POSITIVE LOGITS
    乡
    0.09
    è¦ģä¹Ī
    0.09
    _SEP
    0.09
    çħľ
    0.09
    çIJĨå·¥
    0.09
     mỡ
    0.09
    æĶ¶åıĸ
    0.08
    ifest
    0.08
    ITH
    0.08
    èĤ©èĨĢ
    0.08
    Activations Density 0.187%

    No Known Activations