© 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. 65473
    Prev
    Next
    INDEX
    Explanations

    between water molecules

    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
    èķ
    -0.08
    缸åIJĮ
    -0.08
    ussi
    -0.08
    _SKIP
    -0.07
    fo
    -0.07
    oja
    -0.07
    oS
    -0.07
    ç²Ĺçķ¥
    -0.06
     trôi
    -0.06
    çŁŃæľŁ
    -0.06
    POSITIVE LOGITS
     reversed
    0.08
    åıįåIJij
    0.08
    .reverse
    0.07
     âĨĶ
    0.07
    odox
    0.07
    åıį转
    0.07
    PROP
    0.07
    ÙĦاÙħ
    0.07
     reverse
    0.07
    æĬ½
    0.07
    Activations Density 0.004%

    No Known Activations