© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 11743
    Prev
    Next
    INDEX
    Explanations

    numbers followed by punctuation

    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
    ertools
    -0.10
    nese
    -0.09
    entina
    -0.09
    thouse
    -0.09
    ulina
    -0.09
    ...*
    -0.08
    ElapsedTime
    -0.08
    HTTPHeader
    -0.08
    ésil
    -0.08
    redit
    -0.08
    POSITIVE LOGITS
    wd
    0.07
    -
    0.07
    0.06
    ,
    0.06
    åħ·ä½ĵæݪæĸ½
    0.06
     C
    0.06
    /
    0.06
     supervised
    0.06
    ish
    0.06
     Hell
    0.06
    Activations Density 0.061%

    No Known Activations