© 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. 33320
    Prev
    Next
    INDEX
    Explanations

    the 1960s

    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
    ç±Ģ
    -0.09
    èŁ¾
    -0.08
    设计æĸ¹æ¡Ī
    -0.08
    ÙĥÙĨ
    -0.08
    容纳
    -0.08
     Anc
    -0.08
    æĢ§è´¨
    -0.08
    ä¸İæŶ
    -0.08
    æ¯ıæľĪ
    -0.08
     related
    -0.08
    POSITIVE LOGITS
    æĥķ
    0.10
    磫
    0.10
    ä¸ĸ纪
    0.09
    ooks
    0.09
    æı¡ä½ı
    0.09
    ernet
    0.09
    ç§Łè½¦
    0.09
    .constraints
    0.09
    TRL
    0.08
    缼
    0.08
    Activations Density 0.069%

    No Known Activations