© 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. 22214
    Prev
    Next
    INDEX
    Explanations

    dates and times

    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
     defaultProps
    -0.07
    æĸ°ç¤¾
    -0.07
    imir
    -0.06
    utton
    -0.06
    meer
    -0.06
    åī¯ä¸»å¸Ń
    -0.06
    åĪ°æŶåĢĻ
    -0.06
    ä¸įåıĤåĬł
    -0.06
    Earn
    -0.06
    Mocks
    -0.06
    POSITIVE LOGITS
    é¡¹çĽ®åıĬ
    0.07
    letter
    0.07
    uper
    0.07
    Ñģен
    0.07
    èvre
    0.07
     fingerprint
    0.06
    esian
    0.06
    ITTER
    0.06
    itter
    0.06
    lish
    0.06
    Activations Density 0.029%

    No Known Activations