© 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. 19234
    Prev
    Next
    INDEX
    Explanations

    R documentation `\alias`

    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
    åħ¸åŀĭ
    -0.07
    astle
    -0.07
    printed
    -0.07
    ikat
    -0.07
    åħĪéĶĭ模èĮĥ
    -0.07
    ÙģÙĪ
    -0.07
    Personally
    -0.07
    åIJĮæŶè¿ĺè¦ģ
    -0.07
    ustain
    -0.07
    ihak
    -0.07
    POSITIVE LOGITS
    å¹¶ä½ľ
    0.07
     decis
    0.07
    rir
    0.07
    ؤÙĩا
    0.06
     adj
    0.06
       ↵
    0.06
     íĨµíķľ
    0.06
     Kimber
    0.06
     sandwich
    0.06
    端æŃ£
    0.06
    Activations Density 0.015%

    No Known Activations