© 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. 50135
    Prev
    Next
    INDEX
    Explanations

    rounding to integer or 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
    <|box_end|>
    -0.09
    ä¼łéģĵ
    -0.08
     passive
    -0.08
    زاÙħ
    -0.08
    ieden
    -0.08
    ahal
    -0.08
     sobÄħ
    -0.07
    _MEMBERS
    -0.07
     PROGRAMMA
    -0.07
    åķ¸
    -0.07
    POSITIVE LOGITS
    èĪį
    0.09
    rounded
    0.08
     rounded
    0.08
     rounding
    0.08
     окÑĢÑĥг
    0.08
    .round
    0.07
     approximation
    0.07
     decimal
    0.07
    -rounded
    0.07
    irr
    0.07
    Activations Density 0.026%

    No Known Activations