© 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. 61776
    Prev
    Next
    INDEX
    Explanations

    decimal place rounding

    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
    egrity
    -0.09
    سا
    -0.08
    achtet
    -0.08
    Õ½
    -0.07
    erville
    -0.07
    次è¦ģ
    -0.07
     IMPORT
    -0.07
    ç¬ĭ
    -0.07
    ÙĦÙĥ
    -0.07
    grab
    -0.07
    POSITIVE LOGITS
    æķħæѤ
    0.07
     qw
    0.06
     Wald
    0.06
     formulas
    0.06
    ival
    0.06
    çĶ¨å®ĥ
    0.06
    antar
    0.06
    åºĶçĶ¨äºİ
    0.06
    Backend
    0.06
    ä¾ĭ
    0.06
    Activations Density 0.010%

    No Known Activations