© 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. 50696
    Prev
    Next
    INDEX
    Explanations

    limit notation

    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
    ainties
    -0.09
    edList
    -0.08
    ../../../
    -0.08
    enticate
    -0.08
    ainty
    -0.08
     Ganze
    -0.08
    zal
    -0.08
    JECT
    -0.08
    anjung
    -0.07
    yper
    -0.07
    POSITIVE LOGITS
    sic
    0.08
    siz
    0.07
    gab
    0.07
    s
    0.07
    kut
    0.07
    اÙħ
    0.07
    о
    0.07
    ات
    0.07
    imum
    0.06
    k
    0.06
    Activations Density 0.002%

    No Known Activations