© 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. 45547
    Prev
    Next
    INDEX
    Explanations

    reasonable following words

    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
    unno
    -0.09
    resi
    -0.08
    upu
    -0.08
    iphy
    -0.08
    arki
    -0.08
    Äħż
    -0.08
    rey
    -0.08
    azī
    -0.08
    каÑģ
    -0.08
    arkan
    -0.08
    POSITIVE LOGITS
    -sized
    0.10
    ly
    0.10
    ably
    0.10
     sized
    0.09
    èĮĥåĽ´åĨħ
    0.08
    èĮĥåĽ´åĨħçļĦ
    0.08
    mente
    0.08
     amount
    0.08
    éĻIJ度çļĦ
    0.08
     Sized
    0.07
    Activations Density 0.020%

    No Known Activations