© 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. 15168
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and characters

    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
     bestimm
    -0.07
    好æĥ³
    -0.06
     Baghd
    -0.06
    æ¸Īãģ¿
    -0.06
    каза
    -0.06
    lund
    -0.06
     lục
    -0.06
    istles
    -0.06
    ëĿ½
    -0.06
    ä¸į说è¯Ŀ
    -0.06
    POSITIVE LOGITS
    å±ħé«ĺ
    0.08
    æ°ijé£İ
    0.08
    upi
    0.08
    æ£ł
    0.07
     Gros
    0.07
    åħį费订éĺħ
    0.07
    utel
    0.07
    åIJİèĢħ
    0.07
    epy
    0.07
    驻马
    0.07
    Activations Density 0.005%

    No Known Activations