© 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. 21230
    Prev
    Next
    INDEX
    Explanations

    length, size, or count

    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
    ontan
    -0.08
    -fluid
    -0.08
    adres
    -0.08
    -bel
    -0.07
    -datepicker
    -0.07
     cooler
    -0.07
    onte
    -0.07
    IMER
    -0.07
    åij³éģĵ
    -0.07
    温度为
    -0.07
    POSITIVE LOGITS
     count
    0.10
    NumberOf
    0.10
     تعداد
    0.10
     NumberOf
    0.10
     counting
    0.09
     Äijếm
    0.09
    计æķ°
    0.09
    =length
    0.09
     ÙĪعدد
    0.09
     number
    0.09
    Activations Density 0.153%

    No Known Activations