© 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. 11557
    Prev
    Next
    INDEX
    Explanations

    state definitions

    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
    两件
    -0.07
    LIO
    -0.07
     ÙħÙĪرد
    -0.07
    ikan
    -0.07
    _runtime
    -0.07
    åı¯æĢľ
    -0.07
    è¿ĶåĽŀ顶éĥ¨
    -0.06
    zon
    -0.06
    åķĨè¡Į
    -0.06
     wished
    -0.06
    POSITIVE LOGITS
    çĬ¶æĢģ
    0.10
    çĬ¶æĢģä¸ĭ
    0.09
     State
    0.09
     state
    0.09
    çĬ¶æħĭ
    0.09
    çĬ¶æĢģçļĦ
    0.09
    çĭĢæħĭ
    0.08
    สà¸ĸาà¸Ļะ
    0.08
    ystate
    0.08
    éĺ¶æ®µ
    0.08
    Activations Density 0.018%

    No Known Activations