© 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. 10044
    Prev
    Next
    INDEX
    Explanations

    If you

    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
    orris
    -0.09
    erland
    -0.08
    veillance
    -0.08
    erade
    -0.08
    ehold
    -0.08
    ëŀ¬
    -0.08
    éħĴå±ĭ
    -0.08
     getResult
    -0.08
    á»ĩm
    -0.08
    ÙĪÙĨÙĩ
    -0.08
    POSITIVE LOGITS
    ç±³
    0.06
    adian
    0.06
     ister
    0.06
    åħ¸
    0.06
    ire
    0.06
    iver
    0.06
    avy
    0.06
     Spann
    0.05
    oky
    0.05
    ry
    0.05
    Activations Density 0.002%

    No Known Activations