© 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. 46910
    Prev
    Next
    INDEX
    Explanations

    numbers following specific symbols

    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
    ©
    -0.07
    å°½æľī
    -0.07
    åŃĹæ¯į
    -0.07
    鸾
    -0.07
     Ñģов
    -0.07
    çIJĽ
    -0.07
    é¦Ĵ头
    -0.07
    åı°å±±
    -0.07
    åĿļæĮģä¸įæĩĪ
    -0.06
     compat
    -0.06
    POSITIVE LOGITS
    æĺ¯åħĪ
    0.09
    éľĢè¦ģåħĪ
    0.08
    åħĪå°Ĩ
    0.07
    imini
    0.07
    å¼Ģå±ķ好
    0.07
    å¼Ħæ¸ħ
    0.07
    asal
    0.07
    ä¸īæĿ¿
    0.07
    åħĪåľ¨
    0.07
    imps
    0.07
    Activations Density 0.041%

    No Known Activations