© 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. 34393
    Prev
    Next
    INDEX
    Explanations

    prologue, argument, specific

    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
     Cabang
    -0.08
    åĩĨç¡®æĢ§åĴĮåIJĪæ³ķæĢ§
    -0.08
    ä¼ij
    -0.07
    ละ
    -0.07
    WR
    -0.07
    leman
    -0.07
     pocket
    -0.07
    *out
    -0.07
    UNG
    -0.06
    OUT
    -0.06
    POSITIVE LOGITS
    ritt
    0.07
     berupa
    0.07
     inputs
    0.07
    uÃŁ
    0.06
    ordat
    0.06
    things
    0.06
    ovens
    0.06
    端çļĦ
    0.06
    apsible
    0.06
     Interfaces
    0.06
    Activations Density 0.001%

    No Known Activations