© 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. 57357
    Prev
    Next
    INDEX
    Explanations

    true or false

    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
    eho
    -0.09
    owa
    -0.08
    æĻ¤
    -0.08
    ungk
    -0.08
    finder
    -0.08
    /software
    -0.07
    åįģäºĮæĮĩ
    -0.07
    ÛķÛĮ
    -0.07
    pac
    -0.07
    mund
    -0.07
    POSITIVE LOGITS
    åĵĪ
    0.06
    tring
    0.06
     CharSequence
    0.06
    æľīåĬĽ
    0.06
    iola
    0.06
    false
    0.06
    sene
    0.06
    ulla
    0.06
    åħ¸åŀĭæ¡Īä¾ĭ
    0.06
    éĤ¦
    0.06
    Activations Density 0.008%

    No Known Activations