© 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. 25986
    Prev
    Next
    INDEX
    Explanations

    problem followed by definition or question

    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
    umerator
    -0.08
    olumes
    -0.08
    ons
    -0.08
    imiter
    -0.08
    ibles
    -0.07
    _Msp
    -0.07
    ullen
    -0.07
    ä¸Ģ转
    -0.07
    ستÙĨ
    -0.07
    issan
    -0.07
    POSITIVE LOGITS
    çİ®
    0.07
    gart
    0.07
    plex
    0.07
    isp
    0.07
    orce
    0.06
    çĶ¨å¾®ä¿¡
    0.06
    let
    0.06
     sheet
    0.06
     pains
    0.06
    uze
    0.06
    Activations Density 0.003%

    No Known Activations