© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 64423
    Prev
    Next
    INDEX
    Explanations

    code structures and symbols

    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
    ãĥ«ãĥī
    -0.08
    ares
    -0.08
    dzi
    -0.08
    å©´
    -0.07
    åºĶå¾ģ
    -0.07
    ehren
    -0.07
    Ŀ¼
    -0.07
    ä¸Ģåıij
    -0.07
    zin
    -0.07
    enix
    -0.07
    POSITIVE LOGITS
    tai
    0.07
    _aliases
    0.07
    æį·
    0.07
     carriers
    0.07
     carrier
    0.07
     redirect
    0.06
    æĽ´åĬł
    0.06
    دار
    0.06
     heels
    0.06
     دار
    0.06
    Activations Density 0.064%

    No Known Activations