© 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. 32758
    Prev
    Next
    INDEX
    Explanations

    words in a sentence or line

    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
     addir
    -0.07
    rund
    -0.07
    žd
    -0.07
    route
    -0.07
    åĨĻä¸Ĭ
    -0.07
    éŃģ
    -0.07
    áĢ¸
    -0.07
    AYOUT
    -0.07
    ovens
    -0.07
    å²Ķ
    -0.07
    POSITIVE LOGITS
    éĢĨ
    0.08
     Bryant
    0.07
     invers
    0.07
     smashed
    0.07
    èĢĮåħ¥
    0.06
    ãĤ¹ãĥĥãĤŃãĥª
    0.06
    LK
    0.06
     invertir
    0.06
    inters
    0.06
     togg
    0.06
    Activations Density 0.001%

    No Known Activations