© 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. 31121
    Prev
    Next
    INDEX
    Explanations

    maximal value or number

    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
    ambi
    -0.07
    ä»İä»ĸ
    -0.07
    åĬ¨åĬĽ
    -0.07
    wes
    -0.06
     normally
    -0.06
     lauf
    -0.06
     dere
    -0.06
    è®¤è®¤çľŁ
    -0.06
    ัà¸Ļà¸Ĺ
    -0.06
    åĨįæİ¥
    -0.06
    POSITIVE LOGITS
    /max
    0.09
    scher
    0.09
     maximizing
    0.08
     configurations
    0.08
     maximal
    0.08
    azor
    0.08
    goog
    0.07
    ós
    0.07
     concentrating
    0.07
    eya
    0.07
    Activations Density 0.013%

    No Known Activations