© 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. 55324
    Prev
    Next
    INDEX
    Explanations

    special characters and code fragments

    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
    ories
    -0.07
    EGA
    -0.07
    ::
    -0.07
    /mp
    -0.07
    Derived
    -0.06
    izable
    -0.06
    å¾ĹåĩºçļĦ
    -0.06
     Jup
    -0.06
    ::*
    -0.06
    /DD
    -0.06
    POSITIVE LOGITS
    loh
    0.09
    OTT
    0.07
    wifi
    0.07
    kki
    0.07
    bü
    0.07
    çĶŁç´ł
    0.07
    اÙĨØ´
    0.07
    éĺħè¯»æľ¬æĸĩ
    0.07
    æ¸
    0.07
    段æŶéĹ´
    0.07
    Activations Density 0.579%

    No Known Activations