© 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. 37693
    Prev
    Next
    INDEX
    Explanations

    why this is happening

    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
    ÑĢог
    -0.10
    ÑĤик
    -0.09
    åĻ
    -0.09
    ras
    -0.08
     typ
    -0.08
     memo
    -0.08
     <+
    -0.08
    .memo
    -0.08
    ä¸Ģå®ļçļĦ
    -0.08
    çľĭ
    -0.08
    POSITIVE LOGITS
    æ¢Ĺ
    0.10
    èĶij
    0.10
    é¢ijé¢ij
    0.10
    æĩĭ
    0.09
    èijĨ
    0.09
    æĺŃ
    0.08
    èĥ½æī¾åĪ°
    0.08
    æĿ¥ä¸´
    0.08
    æĿ¥äºĨ
    0.08
    èģĮ
    0.08
    Activations Density 0.160%

    No Known Activations