© 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. 12747
    Prev
    Next
    INDEX
    Explanations

    scores followed by hyphens

    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
    arkin
    -0.07
    ç½ķ
    -0.07
    ignon
    -0.07
    alker
    -0.07
    Som
    -0.06
    elj
    -0.06
    γÏĮ
    -0.06
    åħ«çĻ¾
    -0.06
    èłķ
    -0.06
    _VERBOSE
    -0.06
    POSITIVE LOGITS
    refs
    0.07
    ems
    0.07
    æł¼å°Ķ
    0.07
    loh
    0.07
    _locator
    0.07
    软件ä¸ĭè½½
    0.07
     Eman
    0.07
    å°ģéĹŃå¼ı
    0.07
    饵
    0.07
    è·ij
    0.07
    Activations Density 0.029%

    No Known Activations