© 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. 60823
    Prev
    Next
    INDEX
    Explanations

    numeric parsing and conversion

    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
    ouver
    -0.07
    ály
    -0.07
    åĩĨäºĪ
    -0.07
    æĸĹ
    -0.07
    iori
    -0.07
    æĽ´å¤ļåĽŀçŃĶ
    -0.06
    enberg
    -0.06
    phan
    -0.06
     Hoy
    -0.06
    _canvas
    -0.06
    POSITIVE LOGITS
    éĿĴæ¢ħ
    0.07
    è§Ĩéķľ
    0.07
    åľ¨è¯»
    0.07
     калÑĮ
    0.07
    .deserialize
    0.07
     parseInt
    0.07
     bod
    0.06
    /github
    0.06
    umpt
    0.06
    çħ§
    0.06
    Activations Density 0.002%

    No Known Activations