© 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. 50948
    Prev
    Next
    INDEX
    Explanations

    code delimiters and identifiers

    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
    idah
    -0.08
    uhl
    -0.07
    ular
    -0.07
    idon
    -0.07
    undert
    -0.07
    mess
    -0.07
    })(
    -0.07
    ضÙĬ
    -0.06
    ادÙĦ
    -0.06
    ament
    -0.06
    POSITIVE LOGITS
    utzer
    0.08
    ç´¢
    0.07
    港å¸Ĥ
    0.07
    quiera
    0.07
    ä»ĸä¸Ģ缴
    0.06
    çĦ¶åIJİ
    0.06
    åīįç¨ĭ
    0.06
     belge
    0.06
    isode
    0.06
    æīĢå¾Ĺ
    0.06
    Activations Density 0.014%

    No Known Activations