© 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. 25510
    Prev
    Next
    INDEX
    Explanations

    sequences of numbers

    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
    ëĵĿ
    -0.07
    ype
    -0.07
    ive
    -0.07
    omorphic
    -0.07
    ric
    -0.07
    inei
    -0.07
     heavyweight
    -0.07
    èįŁ
    -0.07
    ura
    -0.06
    REQ
    -0.06
    POSITIVE LOGITS
    alah
    0.09
    infeld
    0.08
    auté
    0.07
    etim
    0.07
    loff
    0.07
    å¼ķå¾Ĺ
    0.07
    çľ¼å¸ĺ
    0.07
    alani
    0.07
    prov
    0.07
    ienst
    0.07
    Activations Density 0.022%

    No Known Activations