© 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. 63555
    Prev
    Next
    INDEX
    Explanations

    at the

    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
    ãģ¦ãģĦ
    -0.08
    icos
    -0.08
    æĢ»è®¡
    -0.08
    黩
    -0.08
    mil
    -0.08
    çĶµéĩı
    -0.08
    æŀ¥
    -0.08
    å½³
    -0.08
     CSL
    -0.08
     pointing
    -0.08
    POSITIVE LOGITS
    fixture
    0.09
    楼
    0.09
    å¯¹ä½ł
    0.09
    åIJĪçIJĨçļĦ
    0.09
    ç»Ĩç»Ĩ
    0.09
    车ç«Ļ
    0.08
    åħ»æ®ĸåľº
    0.08
    宪
    0.08
    åīįæīĢæľª
    0.08
    好转
    0.08
    Activations Density 0.022%

    No Known Activations