© 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. 47584
    Prev
    Next
    INDEX
    Explanations

    scalar physics

    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
    دÙĩ
    -0.07
    erule
    -0.06
    alous
    -0.06
    ow
    -0.06
    ake
    -0.06
    åłĤ
    -0.06
    èĨ¨
    -0.06
    owo
    -0.06
    åĨĮ
    -0.06
    ihat
    -0.05
    POSITIVE LOGITS
    äºĮ代
    0.09
     tonel
    0.08
    éģĤ
    0.08
    èİ·æĤī
    0.07
    ()?.
    0.07
    uzz
    0.07
    ibe
    0.07
    гÑĢо
    0.07
     ëĸ
    0.07
    indr
    0.07
    Activations Density 0.007%

    No Known Activations