© 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. 51422
    Prev
    Next
    INDEX
    Explanations

    NAME as ROLE

    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
    çļĦ两个
    -0.07
    è¿ĺæĺ¯
    -0.07
     pair
    -0.07
    ä¸įæĪIJ
    -0.06
     sub
    -0.06
    uco
    -0.06
    æѤæŶ
    -0.06
    æĶ¾æ°´
    -0.06
     paired
    -0.06
    âĢ¦
    -0.06
    POSITIVE LOGITS
     âĢİ
    0.09
    齡
    0.08
    epad
    0.07
    lande
    0.07
     extras
    0.07
    roh
    0.07
    é¢Ĩè¡Ķ
    0.07
    intes
    0.07
    åħĭç¦ı
    0.07
    angelog
    0.07
    Activations Density 0.175%

    No Known Activations