© 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. 57756
    Prev
    Next
    INDEX
    Explanations

    sections or topics within documents

    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
     yourselves
    -0.10
     bol
    -0.09
    çĪª
    -0.09
    缺
    -0.09
    eye
    -0.09
    çĵ¶é¢Ī
    -0.08
    è¿Ļæĺ¯æĪij们
    -0.08
    æĸ¥
    -0.08
    bol
    -0.08
    веÑģ
    -0.08
    POSITIVE LOGITS
    bens
    0.10
    ä»»èģĮ
    0.10
    å²Ĺä½į
    0.09
    èĽ®
    0.09
    è°ģèĥ½
    0.08
    çĤ¹å¤ļ
    0.08
    ç§ij室
    0.08
    çľĭä¸įåĩº
    0.08
    平淡
    0.08
    argas
    0.08
    Activations Density 0.031%

    No Known Activations