© 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. 61661
    Prev
    Next
    INDEX
    Explanations

    visiting or hosting teams/places

    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
    ä¸Ģ个人
    -0.13
    èĢģ人家
    -0.11
    æĪijå¦Ī
    -0.10
    æŃ¤äºº
    -0.10
    è¿Ļ个人
    -0.10
    ä¸ĢåĢĭ人
    -0.09
    æĹłäºº
    -0.09
    ä¹¾åĿ¤
    -0.09
    å«Ĥ
    -0.09
     finalized
    -0.09
    POSITIVE LOGITS
    ä¸ľäº¬
    0.10
    æĿ¥èĩª
    0.09
    .ak
    0.09
    hone
    0.09
    宿
    0.09
    /native
    0.09
     Alo
    0.09
    å§ĭç»Ī
    0.08
    çŃĭ
    0.08
    aud
    0.08
    Activations Density 0.023%

    No Known Activations