© 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. 33758
    Prev
    Next
    INDEX
    Explanations

    OBD2 DB9 adapter cables

    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
     important
    -0.07
    veli
    -0.07
    åıª
    -0.07
    ynet
    -0.07
     specifics
    -0.06
    _Handle
    -0.06
     videoc
    -0.06
    秤
    -0.06
    éĢŀ
    -0.06
    edes
    -0.06
    POSITIVE LOGITS
    æĢ§æĪĸ
    0.07
    éĶĻ误æĪĸ
    0.07
    人æĪĸ
    0.07
    bolt
    0.07
    ohan
    0.07
    æĪĸå¤ļ个
    0.07
     enten
    0.07
    oma
    0.07
    lob
    0.07
     publicly
    0.07
    Activations Density 0.008%

    No Known Activations