© 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. 13094
    Prev
    Next
    INDEX
    Explanations

    intersection and grep commands

    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
    /if
    -0.07
    odor
    -0.07
    antro
    -0.07
    ãĥ¼ãĥŀ
    -0.06
    ative
    -0.06
    onest
    -0.06
    åħ¶æŀĹ
    -0.06
    bbe
    -0.06
    째
    -0.06
    erness
    -0.06
    POSITIVE LOGITS
    icts
    0.09
    omanip
    0.08
    sWith
    0.08
    عدÙħ
    0.07
     Saj
    0.07
    ä½Ļåľ°
    0.07
    Ú¾ÛĮ
    0.07
     gỡ
    0.07
    oly
    0.07
    ugio
    0.07
    Activations Density 0.002%

    No Known Activations