© 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. 64697
    Prev
    Next
    INDEX
    Explanations

    precede, onMouse, declar

    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
    åIJİèĢħ
    -0.07
    ()._
    -0.07
    ample
    -0.07
    ONUS
    -0.07
    UNCH
    -0.07
     latter
    -0.07
     Dalton
    -0.06
    elser
    -0.06
    haj
    -0.06
    æľīè¿Ļ个
    -0.06
    POSITIVE LOGITS
    _COMPARE
    0.07
    ä¸ĢçĽ´åľ¨
    0.06
    ä¸Ģ个好çļĦ
    0.06
    rov
    0.06
    æĪij们éĥ½çŁ¥éģĵ
    0.06
     zade
    0.06
    _fds
    0.06
    åħ
    0.06
    éļ
    0.06
    ä½Ĩæĺ¯çĶ±äºİ
    0.06
    Activations Density 0.054%

    No Known Activations