© 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. 56631
    Prev
    Next
    INDEX
    Explanations

    researchers examined studies

    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
    éĢłçļĦ
    -0.07
    [J
    -0.07
    pul
    -0.07
    pris
    -0.07
    atever
    -0.07
    å¾Ģå¤ĸ
    -0.07
     dÆ°
    -0.06
    "https
    -0.06
    åıĤè§ģ
    -0.06
    æ°Ľ
    -0.06
    POSITIVE LOGITS
    <|box_end|>
    0.07
    ÑĤаÑĤа
    0.07
    åijĹ
    0.07
    hofer
    0.07
    ằng
    0.07
    åѦ鼷éĶĭ
    0.07
    ãģİ
    0.07
    çļĦå¤ļ
    0.07
    eland
    0.07
    ldb
    0.06
    Activations Density 0.112%

    No Known Activations