© 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. 30014
    Prev
    Next
    INDEX
    Explanations

    next sample

    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
    adore
    -0.07
    AccessException
    -0.07
    orama
    -0.07
    mig
    -0.07
    巨人
    -0.07
    人åĪ°
    -0.07
    /topic
    -0.07
    &M
    -0.07
    _identity
    -0.07
    Indented
    -0.07
    POSITIVE LOGITS
     counter
    0.07
     ÙħÙĨا
    0.07
    ptr
    0.06
     Counter
    0.06
    Counter
    0.06
     appar
    0.06
     Gui
    0.06
    åIJ¬ä¸įæĩĤ
    0.06
    bies
    0.06
    æłĩçļĦ
    0.06
    Activations Density 0.002%

    No Known Activations