© 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. 59753
    Prev
    Next
    INDEX
    Explanations

    shifting up or down

    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
    bin
    -0.07
     unconventional
    -0.07
     syn
    -0.07
    æĮij
    -0.07
     Outside
    -0.07
    Lifecycle
    -0.06
    ç©·
    -0.06
    æ°¸ä¸į
    -0.06
    æĪIJ为åħ¨çIJĥ
    -0.06
    é£ĺ
    -0.06
    POSITIVE LOGITS
    èħ¾
    0.10
    ibera
    0.09
    容纳
    0.09
    æıĴåħ¥
    0.09
    Insert
    0.08
    -insert
    0.08
    -flex
    0.08
    amani
    0.08
    newInstance
    0.08
     nhÆ°á»Ŀng
    0.08
    Activations Density 0.011%

    No Known Activations