© 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. 38921
    Prev
    Next
    INDEX
    Explanations

    fire, days, cascade, male, author, video, activity, space, heavy

    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
    eves
    -0.07
    sembl
    -0.06
    reds
    -0.06
    缩水
    -0.06
    ï½ŀãĢį
    -0.06
    poon
    -0.06
    _STARTED
    -0.06
    夫æĸ¯åŁº
    -0.06
    ients
    -0.06
    ecker
    -0.06
    POSITIVE LOGITS
    äºĮåŃĹ
    0.09
    两个åŃĹ
    0.08
    ä¸Ģè¯į
    0.08
    ãģ¨ãģĦãģĨè¨Ģèijī
    0.08
    ureau
    0.07
    UMMY
    0.07
    mage
    0.07
    vsp
    0.07
    äºĭä¸ļçļĦ
    0.07
    uum
    0.07
    Activations Density 0.085%

    No Known Activations