© 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. 43759
    Prev
    Next
    INDEX
    Explanations

    Honey Ale, Steam generators, Nuclear Watch

    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
    edt
    -0.08
    getragen
    -0.07
    ewnÄĻ
    -0.07
    èĢĥ
    -0.06
    åĩ¡
    -0.06
    éd
    -0.06
    å©·
    -0.06
    æĽĻ
    -0.06
    ernals
    -0.06
    urt
    -0.06
    POSITIVE LOGITS
    ÙĥØ©
    0.08
    laise
    0.07
    .gf
    0.07
    doÄŁan
    0.07
    amique
    0.07
    åĬªåĬĽä¸ĭ
    0.07
    اÙĨÙĪ
    0.07
     hev
    0.07
    ovich
    0.07
    ISIS
    0.07
    Activations Density 0.166%

    No Known Activations