© 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. 24970
    Prev
    Next
    INDEX
    Explanations

    General Public License

    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
    åłª
    -0.08
    à¸ģลาà¸ĩ
    -0.07
    anism
    -0.06
    çĶŁåij½çļĦ
    -0.06
    [array
    -0.06
    shadow
    -0.06
     reten
    -0.06
     Még
    -0.06
    artz
    -0.06
    angling
    -0.06
    POSITIVE LOGITS
    itious
    0.08
    ä½ľåĪĻ
    0.08
    éĥ¨åĪĨåĨħ容
    0.07
    é¢ĦåĮħè£ħ
    0.07
    纶
    0.07
    åľ¨èIJ¥
    0.07
    uet
    0.07
    ingg
    0.07
    uary
    0.07
    lore
    0.07
    Activations Density 0.002%

    No Known Activations