© 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. 24713
    Prev
    Next
    INDEX
    Explanations

    .php, .html, or file path endings

    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
    .Networking
    -0.08
    ough
    -0.07
    )':
    -0.07
    建设éĽĨåĽ¢æľīéĻIJåħ¬åı¸
    -0.07
    raj
    -0.07
    INN
    -0.07
    ingt
    -0.07
    íķĺê²łëĭ¤ëĬĶ
    -0.06
    .uni
    -0.06
    ())->
    -0.06
    POSITIVE LOGITS
    кона
    0.07
    emann
    0.07
    欢è¿İæĤ¨
    0.07
    ista
    0.07
    以ä¸ĭç®Ģ称
    0.07
     ÙĦÙĥرة
    0.07
    Ù°
    0.07
    éĤ£äºĽå¹´
    0.06
    à¸Ļà¹Į
    0.06
    该æĸĩ
    0.06
    Activations Density 0.568%

    No Known Activations