© 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. 56406
    Prev
    Next
    INDEX
    Explanations

    numeric conversions or measurements

    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
    astia
    -0.10
    عدة
    -0.09
     altrett
    -0.09
    theid
    -0.09
    .qml
    -0.09
    éħĴå±ĭ
    -0.09
    écie
    -0.08
    ascar
    -0.08
    è¾Ļ
    -0.08
    enties
    -0.08
    POSITIVE LOGITS
    ↵
    0.08
     mic
    0.07
    /
    0.07
    0.06
     ill
    0.06
    å¨ľ
    0.06
     You
    0.06
    mer
    0.05
    eph
    0.05
     g
    0.05
    Activations Density 0.021%

    No Known Activations