© 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. 1502
    Prev
    Next
    INDEX
    Explanations

    analytical examination

    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
    æĿ°
    -0.08
    GIT
    -0.07
    xee
    -0.07
    aisons
    -0.07
    ãģĦãģĪ
    -0.07
    quelle
    -0.07
    åĴĮè¦ģæ±Ĥ
    -0.07
    elder
    -0.07
    -Za
    -0.07
    altungs
    -0.06
    POSITIVE LOGITS
    amai
    0.08
    çķľ
    0.08
    çĤ¹åIJİ
    0.08
    سÙĤ
    0.08
    idamente
    0.07
    éĹ®é¢ĺæŶ
    0.07
    æĥħåĨµåIJİ
    0.07
    äºĭå®ľ
    0.07
     potreb
    0.07
    istant
    0.06
    Activations Density 1.078%

    No Known Activations