© 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. 38695
    Prev
    Next
    INDEX
    Explanations

    specific technical terms

    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
    .exc
    -0.07
    ONY
    -0.07
    åĬ¡
    -0.07
    illed
    -0.07
    ezd
    -0.07
    'Neill
    -0.07
     Zam
    -0.07
     Opp
    -0.06
    çĮĽåħ½
    -0.06
    nian
    -0.06
    POSITIVE LOGITS
    åĬ©
    0.09
    oha
    0.07
    WithName
    0.07
    inel
    0.07
    resta
    0.07
    oris
    0.07
    amai
    0.07
     pik
    0.07
     ÙħÙħÙĨ
    0.07
     ÑĥÑģÑĤа
    0.07
    Activations Density 0.231%

    No Known Activations