© 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. 34879
    Prev
    Next
    INDEX
    Explanations

    numbered list items

    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
    ajian
    -0.07
    جرÙĬ
    -0.07
    terna
    -0.07
    缸è§ģ
    -0.07
     virt
    -0.07
    ipt
    -0.07
    æĴ
    -0.06
    湧
    -0.06
    elat
    -0.06
    abol
    -0.06
    POSITIVE LOGITS
    nish
    0.07
    apon
    0.07
    nick
    0.07
    aran
    0.06
    è¶Ł
    0.06
    INK
    0.06
     isra
    0.06
    ÑįÑĪ
    0.06
    ãĤ³ãĥ¼ãĥ«
    0.06
    itory
    0.06
    Activations Density 0.005%

    No Known Activations