© 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. 18681
    Prev
    Next
    INDEX
    Explanations

    numeric value or unit

    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
    éĴ°
    -0.08
    ither
    -0.07
    wein
    -0.07
    ropolis
    -0.07
    iggins
    -0.07
    =:
    -0.07
    chs
    -0.07
    cca
    -0.07
    hift
    -0.07
     Rosenstein
    -0.07
    POSITIVE LOGITS
    æķ°åĢ¼
    0.12
     numer
    0.12
     numeric
    0.11
     numerical
    0.11
    à¸ķัวà¹Ģลà¸Ĥ
    0.10
    numeric
    0.09
    numer
    0.09
    _numeric
    0.09
     ìĪ«
    0.08
     numeri
    0.08
    Activations Density 0.010%

    No Known Activations