© 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. 44172
    Prev
    Next
    INDEX
    Explanations

    SQL queries and optimization objectives

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥĥãĤ·
    -0.07
    ibro
    -0.07
    oros
    -0.07
    acos
    -0.07
    éĺħ读åİŁæĸĩ
    -0.06
    /current
    -0.06
    幸è¿IJçļĦæĺ¯
    -0.06
    liš
    -0.06
    æ²¼
    -0.06
    ä¸Ģæĥ³
    -0.06
    POSITIVE LOGITS
    bies
    0.08
    éĩĮåħĭ
    0.07
    agio
    0.07
    rauch
    0.07
    åk
    0.07
    èī¯
    0.07
     motivated
    0.07
    /min
    0.06
    æĿľ
    0.06
     Chambres
    0.06
    Activations Density 0.017%

    No Known Activations