© 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. 39732
    Prev
    Next
    INDEX
    Explanations

    mathematical notation ($$, ., fractions)

    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
    illac
    -0.09
    çıįåĵģ
    -0.08
    itage
    -0.08
    onsin
    -0.08
     risp
    -0.08
    testdata
    -0.08
    _INITIALIZ
    -0.08
    inspace
    -0.08
    amá
    -0.08
    olation
    -0.08
    POSITIVE LOGITS
    èĭ¥
    0.07
    è¦ģ
    0.07
     if
    0.07
    åľ¨
    0.06
    åı¦ä¸Ģæĸ¹éĿ¢
    0.06
     íķľíݸ
    0.06
    è¦ģ使
    0.06
    çĶ±äºİ
    0.06
    è¦ģä¿Ŀè¯ģ
    0.06
    è¦ģ让
    0.06
    Activations Density 0.013%

    No Known Activations