© 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. 31268
    Prev
    Next
    INDEX
    Explanations

    special characters and numbers after Âł

    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
    iggers
    -0.08
    veloper
    -0.08
    anker
    -0.08
    okrat
    -0.08
    ipple
    -0.08
    ertian
    -0.08
    berat
    -0.08
    ebro
    -0.08
    otte
    -0.08
    igrated
    -0.08
    POSITIVE LOGITS
    isations
    0.08
    æīĢæľª
    0.06
    âĢij
    0.06
    &amp
    0.06
    ais
    0.06
    aÅŁ
    0.06
    a
    0.06
     ris
    0.06
    _SY
    0.06
    <
    0.05
    Activations Density 0.064%

    No Known Activations