© 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. 27250
    Prev
    Next
    INDEX
    Explanations

    equations with numbers 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
    emar
    -0.08
    æĹłå¿ĥ
    -0.08
    asca
    -0.08
    겸
    -0.07
    å°½èĩªå·±
    -0.07
    æīĢæľª
    -0.07
    è²ī
    -0.07
    åĬ¨èĦī硬åĮĸ
    -0.07
    halle
    -0.07
    beck
    -0.06
    POSITIVE LOGITS
    ":[
    0.07
    éķĤ
    0.07
    ochrome
    0.06
    -needed
    0.06
    atz
    0.06
    rd
    0.06
     additional
    0.06
    gad
    0.06
    arius
    0.06
    uns
    0.06
    Activations Density 0.002%

    No Known Activations