© 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. 43028
    Prev
    Next
    INDEX
    Explanations

    setting goals

    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
    anyak
    -0.07
    é¼ĵ
    -0.07
    ign
    -0.07
    æĭ¼
    -0.07
    ignet
    -0.07
    igy
    -0.07
     Système
    -0.07
    asst
    -0.07
    agher
    -0.06
    Õ²
    -0.06
    POSITIVE LOGITS
    çĮ
    0.07
    zin
    0.07
     pro
    0.07
    opf
    0.07
    ĵ¨
    0.07
    ibert
    0.07
    etter
    0.07
    amb
    0.06
    ambul
    0.06
     McConnell
    0.06
    Activations Density 0.050%

    No Known Activations