© 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. 11469
    Prev
    Next
    INDEX
    Explanations

    dental and cellular communications

    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
    沧
    -0.11
    ä¸ģ
    -0.10
    åijĹ
    -0.09
    .Modules
    -0.09
    езÑĥлÑĮÑĤ
    -0.09
    pas
    -0.09
    å½¼
    -0.08
    _bases
    -0.08
    åıijåŀĭ
    -0.08
    idon
    -0.08
    POSITIVE LOGITS
    _TD
    0.09
    æĢĢ
    0.09
    ÑĢиÑģ
    0.09
    æĿ¥è¢Ń
    0.09
    æ¯ı个人çļĦ
    0.09
    èijĹ
    0.09
    åģļå¾Ĺ
    0.08
    à¹Ĥà¸Ľà¸£à¸Ķ
    0.08
    责任
    0.08
    ä»»ä½ķ人
    0.08
    Activations Density 0.105%

    No Known Activations