© 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. 57775
    Prev
    Next
    INDEX
    Explanations

    Internet Explorer

    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
    Arrays
    -0.07
    latlong
    -0.07
    æĤ£
    -0.07
    .Entry
    -0.07
    arend
    -0.07
    Ùıب
    -0.07
    丽èIJį
    -0.07
    ervi
    -0.07
    彦
    -0.07
    åħ·ä½ĵå¦Ĥä¸ĭ
    -0.06
    POSITIVE LOGITS
    `;
    0.07
    alfa
    0.07
    ech
    0.06
    ”;
    0.06
    ;</
    0.06
    æĬĢæľ¯çłĶ究
    0.06
     ";
    0.06
    UDGE
    0.06
    zion
    0.06
    "';
    0.06
    Activations Density 0.065%

    No Known Activations