© 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. 55677
    Prev
    Next
    INDEX
    Explanations

    numbers and units

    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
    nung
    -0.08
    quin
    -0.07
    é¹Ĭ
    -0.07
    ovin
    -0.07
    ustos
    -0.07
    天é¾Ļ
    -0.07
    nungs
    -0.07
    étique
    -0.07
    _Construct
    -0.07
    uder
    -0.07
    POSITIVE LOGITS
    åħ¨èĥ½
    0.07
    .multi
    0.07
    éĨī
    0.07
    æ¦Ħ
    0.07
    kob
    0.07
    _MACRO
    0.06
    éĴŀ
    0.06
    æĿľåħ°çī¹
    0.06
    oom
    0.06
     Rua
    0.06
    Activations Density 0.109%

    No Known Activations