© 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. 22254
    Prev
    Next
    INDEX
    Explanations

    below is a

    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
    -0.08
    iele
    -0.08
    ↵
    -0.06
    ms
    -0.06
    横
    -0.06
    ä»Ĭ
    -0.06
    imin
    -0.06
    çĶŁæ°Ķ
    -0.06
    èĻŀ
    -0.06
    òi
    -0.05
    POSITIVE LOGITS
    bons
    0.08
     spiagg
    0.08
    LOUR
    0.08
    áŀ¸
    0.08
    yssey
    0.08
    assi
    0.08
    æĹ¥æ¸¸
    0.08
    anky
    0.08
    OutOfBounds
    0.08
    LEY
    0.08
    Activations Density 0.002%

    No Known Activations