© 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. 26689
    Prev
    Next
    INDEX
    Explanations

    the digit 8

    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
    emun
    -0.07
     nonatomic
    -0.07
    rips
    -0.07
    iants
    -0.07
    untr
    -0.07
    itionally
    -0.07
     rtrim
    -0.07
    plaats
    -0.07
    áĢ±áĢ¬
    -0.07
    itous
    -0.07
    POSITIVE LOGITS
    eenth
    0.12
    undheit
    0.08
    essler
    0.08
    евой
    0.08
    bows
    0.07
    ness
    0.07
    æĪIJæĸ°
    0.07
    wald
    0.07
    ear
    0.07
    estad
    0.07
    Activations Density 0.433%

    No Known Activations