© 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. 64847
    Prev
    Next
    INDEX
    Explanations

    audio/visual apparatuses

    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
     Whip
    -0.07
    atron
    -0.07
    ommen
    -0.07
     whip
    -0.07
    eters
    -0.07
    Pg
    -0.06
    omia
    -0.06
     clash
    -0.06
    gio
    -0.06
    vey
    -0.06
    POSITIVE LOGITS
    ANH
    0.08
    UIS
    0.07
    è²ŀ
    0.07
    Úº
    0.07
    ndon
    0.07
    WithValue
    0.07
     Чи
    0.07
    eren
    0.07
    åħĭéļ¾
    0.07
    uset
    0.06
    Activations Density 0.003%

    No Known Activations