© 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. 33532
    Prev
    Next
    INDEX
    Explanations

    web framework routing

    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
    eron
    -0.09
    ariat
    -0.07
    fran
    -0.07
     ÑģекÑĥ
    -0.07
    /light
    -0.07
    ariate
    -0.07
    +xml
    -0.07
     lightly
    -0.07
     Nazar
    -0.06
    ISTI
    -0.06
    POSITIVE LOGITS
    åĩºäº§
    0.07
     ~(
    0.07
     Area
    0.07
    ored
    0.06
    ä¸ľè·¯
    0.06
    impan
    0.06
    å¼Ĭ
    0.06
    娩
    0.06
    çļĦä¸ĢåĪĩ
    0.06
    èĮĥåĽ´åĨħ使çĶ¨
    0.06
    Activations Density 0.001%

    No Known Activations