© 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. 28154
    Prev
    Next
    INDEX
    Explanations

    select, use, or enable

    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
    æĸĹ
    -0.08
    æ¯ıæ¯ı
    -0.08
    åĵªæĢķæĺ¯
    -0.08
    åĩºæĿ¥ãĤĭ
    -0.08
    å±ħçĦ¶
    -0.07
     Arch
    -0.07
    çĬ¶
    -0.07
    循
    -0.07
    帽åŃIJ
    -0.07
    (util
    -0.07
    POSITIVE LOGITS
    æ·¦
    0.09
    æľ¬æľŁ
    0.09
    ãģ»ãģĭ
    0.08
    æ´ĩ
    0.08
    æľīå¿ħè¦ģ
    0.08
    CADE
    0.08
    è¡į
    0.08
    ç«ĸ
    0.08
    OLE
    0.08
    stantiate
    0.08
    Activations Density 0.373%

    No Known Activations