© 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. 37541
    Prev
    Next
    INDEX
    Explanations

    introducing a topic or detail

    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
    oot
    -0.08
     nonzero
    -0.07
    pees
    -0.07
    ocha
    -0.07
    cestor
    -0.07
    åħ¶ä¸ŃåĮħæĭ¬
    -0.07
    OrNil
    -0.07
     Id
    -0.07
    å¾Ĺèµ·
    -0.07
    å°ıåı¶
    -0.06
    POSITIVE LOGITS
    详
    0.08
    jat
    0.07
    achs
    0.07
    罪
    0.07
    ç±³åĭĴ
    0.07
    bens
    0.07
    æĸĩæĺİ
    0.07
    OPA
    0.07
    (confirm
    0.07
    象
    0.07
    Activations Density 0.099%

    No Known Activations