© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 20486
    Prev
    Next
    INDEX
    Explanations

    format and structure specifications

    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
    丰
    -0.08
    念念
    -0.07
    irl
    -0.07
    NullOr
    -0.06
     Sil
    -0.06
    æĿĥ
    -0.06
    çĦ¶å¤§
    -0.06
    åľ¨çľģ
    -0.06
     buff
    -0.06
     заÑĢÑĥб
    -0.06
    POSITIVE LOGITS
    ets
    0.08
    ayu
    0.07
    etting
    0.07
    ismus
    0.07
     безо
    0.07
    apg
    0.07
     Detected
    0.07
    è¾ĵåĩºçļĦ
    0.06
    undes
    0.06
    èĬĤæĹ¥å¿«ä¹IJ
    0.06
    Activations Density 0.001%

    No Known Activations