© 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. 43497
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    tav
    -0.09
    hed
    -0.09
    istar
    -0.08
    utu
    -0.08
    ubb
    -0.08
     ViewPager
    -0.07
    ارÙĬØ©
    -0.07
     koncep
    -0.07
    å¾Ħ
    -0.07
    rš
    -0.07
    POSITIVE LOGITS
    Âł
    0.09
    lasses
    0.07
    ford
    0.07
    ³³
    0.06
    áĢ·
    0.06
    ErrorMsg
    0.06
    brig
    0.06
    omes
    0.06
    íĮ
    0.06
    åľ¨åįĬ
    0.06
    Activations Density 0.000%

    No Known Activations