© 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. 27719
    Prev
    Next
    INDEX
    Explanations

    sorting numbers or code tokens

    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
    åī¯å¤Ħéķ¿
    -0.07
    è¡Įä¸ļå¸Ĥåľº
    -0.07
    主è¦ģ表çİ°åľ¨
    -0.07
    hoot
    -0.07
    çĵ¦å°Ķ
    -0.07
    AVAILABLE
    -0.07
    è¿ĩåī©
    -0.07
    eli
    -0.07
     Wa
    -0.07
    hari
    -0.07
    POSITIVE LOGITS
    orage
    0.06
    ledge
    0.06
     noexcept
    0.06
    åĴĮå°ļ
    0.06
    Dub
    0.06
    antino
    0.06
    éĻµ
    0.06
    åľ°çĵľ
    0.06
    çĪ¶
    0.06
    ax
    0.06
    Activations Density 0.374%

    No Known Activations