© 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. 2868
    Prev
    Next
    INDEX
    Explanations

    digits and string conversions

    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
    ä¸ĩåį·
    -0.09
    avel
    -0.07
    ÙĤÙī
    -0.07
    ptune
    -0.07
    檸
    -0.07
    ovas
    -0.07
    秩
    -0.07
     Mort
    -0.07
     piv
    -0.07
    ç¾İæĸĩ
    -0.07
    POSITIVE LOGITS
     digits
    0.09
    Digits
    0.09
    digits
    0.08
    çĵ£
    0.08
    concat
    0.08
     vowels
    0.07
    _digits
    0.07
    вл
    0.07
    OPS
    0.07
     maxLength
    0.07
    Activations Density 0.005%

    No Known Activations