© 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. 20183
    Prev
    Next
    INDEX
    Explanations

    .cs file extensions

    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
    Ñĥго
    -0.08
    aglio
    -0.07
    ooter
    -0.07
    moi
    -0.07
    bonne
    -0.07
    .lastIndexOf
    -0.07
    AKE
    -0.07
    idou
    -0.07
    è¿Ļä¸ĢåĪĩ
    -0.07
    mise
    -0.06
    POSITIVE LOGITS
     pertin
    0.06
    _deleted
    0.06
     Rem
    0.06
    第ä¸ĢçĻ¾åĽĽ
    0.06
    /Delete
    0.06
     Manz
    0.06
    깨
    0.06
     dela
    0.06
    ffc
    0.06
    å°Ħ
    0.05
    Activations Density 0.630%

    No Known Activations