© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 49944
    Prev
    Next
    INDEX
    Explanations

    Dr. or R.id

    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
    ãĤ¥
    -0.08
    incr
    -0.07
    ussin
    -0.07
    dei
    -0.07
    ogh
    -0.06
    inci
    -0.06
    æĢİä¹Īçİ©
    -0.06
    edel
    -0.06
    æ¾İ
    -0.06
    wards
    -0.06
    POSITIVE LOGITS
    ł
    0.08
    -angle
    0.07
    enna
    0.07
    даÑĩа
    0.07
    áĢĦáĢº
    0.07
     (!((
    0.07
    Êľ
    0.07
    ähler
    0.07
    éĿĴ天
    0.07
    ariant
    0.07
    Activations Density 0.001%

    No Known Activations