© 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. 60777
    Prev
    Next
    INDEX
    Explanations

    years or over

    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
     Garner
    -0.08
    áĥļáĥĿáĥij
    -0.07
    .pan
    -0.07
    aste
    -0.07
    ehme
    -0.07
     ì¤ijìĹIJìĦľ
    -0.07
    embe
    -0.07
    ãģĻãģĻ
    -0.07
    regor
    -0.07
    enson
    -0.07
    POSITIVE LOGITS
    åıĬ以ä¸Ĭ
    0.18
    以ä¸Ĭ
    0.14
    åıĬ以ä¸ĬçļĦ
    0.13
    人以ä¸Ĭ
    0.13
    以ä¸ĬçļĦ
    0.13
     onwards
    0.13
    米以ä¸Ĭ
    0.13
     ìĿ´ìĥģ
    0.13
    åħĥ以ä¸Ĭ
    0.12
    æĪĸ以ä¸Ĭ
    0.12
    Activations Density 0.317%

    No Known Activations