© 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. 22072
    Prev
    Next
    INDEX
    Explanations

    PATH set in mqsiprofile

    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
    ingleton
    -0.08
    <|box_end|>
    -0.08
    .jdbc
    -0.07
    elik
    -0.07
    鸳
    -0.07
    icamente
    -0.07
    áÄį
    -0.07
    ovol
    -0.07
    ting
    -0.07
    onex
    -0.07
    POSITIVE LOGITS
     Lod
    0.07
    eter
    0.06
    ยà¸Ļ
    0.06
     âĢº
    0.06
    ниÑģ
    0.06
    etzen
    0.06
    лаÑħ
    0.06
    nis
    0.06
    _be
    0.06
    ç§įçļĦ
    0.06
    Activations Density 0.001%

    No Known Activations