© 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. 10019
    Prev
    Next
    INDEX
    Explanations

    constructor context

    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
    éĢĤå½ĵçļĦ
    -0.07
    .localtime
    -0.07
    zum
    -0.07
    iek
    -0.07
    rzy
    -0.07
    ñado
    -0.06
    åIJĵå¾Ĺ
    -0.06
    å¦Ĥéģĩ
    -0.06
    ä¸įä¸ĭåİ»äºĨ
    -0.06
    rome
    -0.06
    POSITIVE LOGITS
    ool
    0.08
    å®ļåŀĭ
    0.07
     genannten
    0.06
    маÑģ
    0.06
    itness
    0.06
    å®ļäºİ
    0.06
    plate
    0.06
    éĮ¦
    0.06
    并åĪ©çĶ¨
    0.06
     HEIGHT
    0.06
    Activations Density 0.036%

    No Known Activations