© 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. 3694
    Prev
    Next
    INDEX
    Explanations

    "isn't" and "doesn't"

    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
    اÙĨÙĬا
    -0.08
    loat
    -0.07
    اتÙĩ
    -0.07
    erat
    -0.07
    OCUS
    -0.07
    VERY
    -0.07
    ä¸įå¾Ĺ以任ä½ķ
    -0.07
    oice
    -0.07
    اتÙĩÙħ
    -0.07
    à¥įà¤ŀ
    -0.07
    POSITIVE LOGITS
    ¯
    0.10
    ãĥ¼
    0.10
    ’t
    0.09
    't
    0.08
    ter
    0.08
    Ķ
    0.08
     siquiera
    0.08
    ê¹IJ
    0.08
    à°ļà±įà°ļ
    0.08
    ¬
    0.07
    Activations Density 0.096%

    No Known Activations