© 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. 40136
    Prev
    Next
    INDEX
    Explanations

    valid solutions

    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
    oin
    -0.08
    á»ĭp
    -0.07
    uentes
    -0.07
    ÙĤطع
    -0.07
     margins
    -0.07
    ross
    -0.07
    uens
    -0.07
    ç´³
    -0.07
     Tend
    -0.07
    Assertions
    -0.07
    POSITIVE LOGITS
    åħ±æľī
    0.08
     valid
    0.08
    valid
    0.07
    符åIJĪæĿ¡ä»¶çļĦ
    0.07
    ä¸Ģåħ±æľī
    0.07
    banyak
    0.07
    _valid
    0.07
    é¢Ĩ
    0.07
     solutions
    0.07
    Configs
    0.06
    Activations Density 0.033%

    No Known Activations