© 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. 37701
    Prev
    Next
    INDEX
    Explanations

    /New_York

    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
    jer
    -0.08
    สิà¹īà¸Ļ
    -0.08
    IDOS
    -0.08
    odin
    -0.08
    人åıĹ伤
    -0.08
    /rec
    -0.08
    åºĶå½ĵä¾Ŀçħ§
    -0.08
    dana
    -0.08
    laise
    -0.07
    mén
    -0.07
    POSITIVE LOGITS
     Hor
    0.07
    Hor
    0.07
    åĽºå®ļ
    0.06
     universal
    0.06
    N
    0.06
     Adv
    0.06
    M
    0.06
    éħ¸
    0.06
     Universal
    0.06
    æĹłè®º
    0.06
    Activations Density 0.054%

    No Known Activations