© 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. 64803
    Prev
    Next
    INDEX
    Explanations

    serializable data

    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
    ä¿Ŀéļľå·¥ä½ľ
    -0.08
    èį·å°ĶèĴĻ
    -0.08
    conn
    -0.08
    DirectoryName
    -0.07
    ĩ
    -0.07
    BLOCK
    -0.07
    ves
    -0.07
    ìĭłë¬¸
    -0.07
    reja
    -0.07
    å¼ĢåĬ¨
    -0.07
    POSITIVE LOGITS
     berupa
    0.08
    æĺİäºĨ
    0.07
    ereal
    0.06
    oya
    0.06
    Triple
    0.06
    alde
    0.06
    ArrayOf
    0.06
     objects
    0.06
    çĹĽ
    0.06
    ä¸Ķæľī
    0.06
    Activations Density 0.003%

    No Known Activations