© 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. 28960
    Prev
    Next
    INDEX
    Explanations

    one, single, few, some

    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
    ENSE
    -0.06
    çĶ«
    -0.06
    ijn
    -0.06
    ä¸ĩä¼Ĺ
    -0.06
    ienz
    -0.06
    åİļçĪ±
    -0.06
    åIJįä¸ĭ
    -0.06
    åIJĦ大
    -0.06
    (*(
    -0.06
     sands
    -0.06
    POSITIVE LOGITS
     olyan
    0.09
    /remove
    0.09
    hada
    0.08
     à¤IJसà¥ĩ
    0.08
    çļĦéĿŀ
    0.08
    è¿Ļæł·çļĦæĥħåĨµ
    0.08
    urt
    0.08
    .timedelta
    0.08
    such
    0.07
    æĺİæĺ¾çļĦ
    0.07
    Activations Density 0.109%

    No Known Activations