© 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. 51855
    Prev
    Next
    INDEX
    Explanations

    dividing numbers

    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
    çĺª
    -0.07
    거리
    -0.07
    agni
    -0.06
     abyss
    -0.06
    LEE
    -0.06
    èį¯
    -0.06
    滩
    -0.06
    å¢Ļè§Ĵ
    -0.06
     tal
    -0.06
    _statuses
    -0.06
    POSITIVE LOGITS
     dividing
    0.10
    åĪĨéħį
    0.09
    åĪĨéħįåĪ°
    0.09
    åĪĨåĪ°
    0.08
     divide
    0.08
     membag
    0.08
     divides
    0.08
    åĪĨæĭħ
    0.08
    division
    0.08
    æ¯ıä½į
    0.08
    Activations Density 0.026%

    No Known Activations