© 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. 39197
    Prev
    Next
    INDEX
    Explanations

    Field of invention or description headings

    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
    tring
    -0.09
    ique
    -0.09
    imson
    -0.09
    ãģĮãĤī
    -0.09
    弯
    -0.08
     amsterdam
    -0.08
     Vaugh
    -0.08
    akk
    -0.08
    aldi
    -0.08
    æijĦ
    -0.08
    POSITIVE LOGITS
    æľīæĦıä¹ī
    0.10
    èĮ«çĦ¶
    0.10
    è¡ħ
    0.09
    çīĿ
    0.09
    涪
    0.09
    æĢ¼
    0.09
    çĸ±
    0.09
    åĿ³
    0.09
    ç¨ļ
    0.09
     Yuk
    0.09
    Activations Density 0.024%

    No Known Activations