© 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. 2122
    Prev
    Next
    INDEX
    Explanations

    monoliths, landscapes, storms, debris, validity

    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
     soothing
    -0.06
    gol
    -0.06
     placebo
    -0.06
    itty
    -0.06
    imet
    -0.06
    )._
    -0.06
    زا
    -0.06
    motions
    -0.05
     gears
    -0.05
    ilde
    -0.05
    POSITIVE LOGITS
     remnants
    0.09
    åħ¸åŀĭçļĦ
    0.09
    åħ¸åŀĭ
    0.09
     locally
    0.08
    æİĸ
    0.08
     kiá»ĥu
    0.08
    åĪ°æĻļ
    0.08
    åľ¨å½ĵåľ°
    0.08
    variably
    0.08
    é¡ŀåŀĭ
    0.08
    Activations Density 0.039%

    No Known Activations