© 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. 42946
    Prev
    Next
    INDEX
    Explanations

    patent numbers

    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
    irc
    -0.08
    ä¸įè¦ģè½»æĺĵ
    -0.07
    lan
    -0.07
    _OPER
    -0.07
    inger
    -0.07
    ascar
    -0.07
    íĮĮ
    -0.06
    erson
    -0.06
    ops
    -0.06
    jay
    -0.06
    POSITIVE LOGITS
    ontage
    0.08
    iful
    0.07
    fully
    0.07
    ATURA
    0.07
    ило
    0.07
    uglify
    0.07
    acqu
    0.07
    aglio
    0.07
    atively
    0.07
    èĭį
    0.07
    Activations Density 0.035%

    No Known Activations