© 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. 37985
    Prev
    Next
    INDEX
    Explanations

    ions and voltage

    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
    æijĬ
    -0.08
    epat
    -0.08
     parts
    -0.07
    ostar
    -0.07
    _increment
    -0.07
     increment
    -0.07
     induk
    -0.06
     fri
    -0.06
     tasse
    -0.06
     litt
    -0.06
    POSITIVE LOGITS
    éĢļéĢı
    0.09
    .static
    0.08
    æ°ı
    0.08
    erner
    0.08
    robe
    0.07
     hypothetical
    0.07
    endor
    0.07
    elec
    0.07
    åĬłæĿĥ
    0.07
    reed
    0.07
    Activations Density 0.007%

    No Known Activations