© 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. 56118
    Prev
    Next
    INDEX
    Explanations

    sum of

    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
    en
    -0.08
    agh
    -0.08
    åĩºä¸į
    -0.07
    aging
    -0.07
    enet
    -0.07
    enix
    -0.07
    akil
    -0.07
    人æľī
    -0.07
    uen
    -0.07
    dda
    -0.07
    POSITIVE LOGITS
     contents
    0.07
    æīĢæľī
    0.07
     consecutive
    0.07
     two
    0.07
    ĵ
    0.07
    leven
    0.07
     contributions
    0.07
    ":[{"
    0.07
    reif
    0.07
    ushman
    0.07
    Activations Density 0.009%

    No Known Activations