© 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. 56175
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and transformations

    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
    adol
    -0.07
    shine
    -0.07
    (png
    -0.06
    åijĬè¯īè®°èĢħ
    -0.06
    èİ·æĤī
    -0.06
    k
    -0.06
    apun
    -0.06
    always
    -0.06
    .addTo
    -0.06
     encar
    -0.06
    POSITIVE LOGITS
    ì¢Į
    0.08
    ibat
    0.08
    çĵ¢
    0.07
    èݱçī¹
    0.07
    orit
    0.07
    ña
    0.07
    转èĢĮ
    0.07
    åĨįçĶ±
    0.07
    owie
    0.07
    اÙĩ
    0.07
    Activations Density 0.003%

    No Known Activations