© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9689
    Prev
    Next
    INDEX
    Explanations

    location and proximity

    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
    æĥħæĻ¯
    -0.10
    à¹Ĥà¸Ħ
    -0.10
    æŃĮ
    -0.09
    GetInt
    -0.09
    å··
    -0.09
    沨
    -0.09
    缤
    -0.09
    LookAndFeel
    -0.09
    åł¨
    -0.09
    åıįè¿ĩæĿ¥
    -0.09
    POSITIVE LOGITS
    çļĦç¼ĺæķħ
    0.10
    ä¸Ŀ绸ä¹ĭè·¯
    0.10
    éŀŃ
    0.09
    交éĢļæŀ¢çº½
    0.08
    å¾Īå¤ļäºĭæĥħ
    0.08
    京津åĨĢ
    0.08
    éĢļå¾Ģ
    0.08
    çŃīåİŁåĽł
    0.08
    ä¼ĺè¶Ĭ
    0.08
    許å¤ļ
    0.08
    Activations Density 0.078%

    No Known Activations