© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 44346
    Prev
    Next
    INDEX
    Explanations

    clin , photos , it , we

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    esus
    -0.08
    wert
    -0.08
    omos
    -0.07
    éĤ£ä»ĸ
    -0.07
    estia
    -0.07
    èģĮä¸ļåѦéĻ¢
    -0.07
    ÑĢÑı
    -0.07
    ehold
    -0.07
    Uuid
    -0.07
    iol
    -0.07
    POSITIVE LOGITS
    uku
    0.09
    ä¸Ķä¸į
    0.08
    注æĦıçļĦæĺ¯
    0.08
    ä¸Ķ
    0.08
    çŀİ
    0.08
    ä¸Ķåľ¨
    0.07
    çŃīçī¹çĤ¹
    0.07
    ãģıãĤĮ
    0.06
     except
    0.06
    except
    0.06
    Activations Density 0.519%

    No Known Activations