© 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. 45193
    Prev
    Next
    INDEX
    Explanations

    end of sentence

    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
    为æĤ¨æݨèįIJ
    -0.08
    è¾¾åħĭ
    -0.07
     Rodr
    -0.07
    ç¿»æĶĿ
    -0.07
    æĬ½æ°´
    -0.07
    æľ«
    -0.07
    uster
    -0.07
    æķĻèĤ²ç½ij
    -0.07
    onso
    -0.07
    InMillis
    -0.07
    POSITIVE LOGITS
    Âł
    0.07
     hại
    0.06
    èķ¾
    0.06
    ATEN
    0.06
    çŀ©çĽ®
    0.06
    iT
    0.06
    æł¸å®ļ
    0.06
    åįĥä¸ĩåĪ«
    0.06
    /cgi
    0.06
    pod
    0.06
    Activations Density 0.139%

    No Known Activations