© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 51890
    Prev
    Next
    INDEX
    Explanations

    decimal places

    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
    lesa
    -0.10
    IGH
    -0.09
    ä»Ģä¹Ī人
    -0.09
    ologa
    -0.09
    _ste
    -0.09
    lopen
    -0.09
    ç«ĭæĸ°
    -0.09
    IGIN
    -0.09
    导è¯Ń
    -0.08
    queta
    -0.08
    POSITIVE LOGITS
    çĻ¾
    0.07
     digits
    0.07
     decimal
    0.07
    after
    0.07
    èĬ±çĵ£
    0.07
    1
    0.06
    Decimal
    0.06
    ches
    0.06
    å°ıæķ°
    0.06
    ç´§éĤ»
    0.06
    Activations Density 0.004%

    No Known Activations