© 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. 49220
    Prev
    Next
    INDEX
    Explanations

    numbers, units, or measurements

    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
    åıªä¸įè¿ĩæĺ¯
    -0.07
    amp
    -0.07
    slaught
    -0.07
    ampi
    -0.07
    kek
    -0.07
     Kub
    -0.07
    føl
    -0.07
    åĪ°è¿ĩ
    -0.06
    atto
    -0.06
    ä¸Ģä¸Ŀä¸įèĭŁ
    -0.06
    POSITIVE LOGITS
    对åºĶçļĦ
    0.08
    对åºĶ
    0.08
     corresponde
    0.07
    ãģ«å¯¾å¿ľ
    0.07
     corresponds
    0.07
    ä¸ĭ表
    0.07
    è°Ĭ
    0.07
    indic
    0.07
     corresponding
    0.06
    ascar
    0.06
    Activations Density 0.011%

    No Known Activations