© 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. 11495
    Prev
    Next
    INDEX
    Explanations

    on [platform/community/location]

    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
    天çĶŁ
    -0.09
    aled
    -0.08
    åĢļ
    -0.08
     yuk
    -0.08
    عاÙħ
    -0.08
    forcer
    -0.08
    oop
    -0.08
     Fall
    -0.08
     Urg
    -0.08
    DSA
    -0.08
    POSITIVE LOGITS
    æīĩ
    0.10
    寤
    0.09
    åıĮéĩį
    0.09
     ÑģайÑĤа
    0.09
    ä¸Ģå®ļç¨ĭ度
    0.09
    äºĴ
    0.09
    æĦıæĦ¿
    0.09
     skys
    0.08
    ivable
    0.08
    æĹ¥è¶ĭ
    0.08
    Activations Density 0.089%

    No Known Activations