© 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. 28477
    Prev
    Next
    INDEX
    Explanations

    you or a

    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
    —
    -0.08
    —and
    -0.07
     toward
    -0.07
     poised
    -0.07
    —but
    -0.07
      ↵
    -0.07
    :
    -0.07
     ...
    -0.06
    —not
    -0.06
    —a
    -0.06
    POSITIVE LOGITS
     Firstly
    0.08
    äºĴçĽ¸å¸®åĬ©
    0.08
    ä»Ģä¹Īåij¢
    0.08
    istos
    0.08
    ente
    0.08
    ç´§ç´§åľ°
    0.08
    å¸Ĥä¸Ń级人æ°ijæ³ķéĻ¢
    0.08
    åľ¨è¿Ļ个æŶåĢĻ
    0.08
    çŁ¥éģĵåIJĹ
    0.08
    icter
    0.08
    Activations Density 0.005%

    No Known Activations