© 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. 38388
    Prev
    Next
    INDEX
    Explanations

    cause or effect

    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
    apore
    -0.08
    ierer
    -0.08
    edBy
    -0.07
    *))
    -0.07
    dbus
    -0.07
    éĩĩ访æŶ
    -0.07
    _BEFORE
    -0.07
    使çĶ¨åIJİ
    -0.07
     During
    -0.07
    Assembler
    -0.07
    POSITIVE LOGITS
    ç«ĭåĪ»
    0.08
    ç«ĭ马
    0.07
     instantly
    0.07
    éļıä¹ĭ
    0.07
    ervlet
    0.07
    engt
    0.06
    ÅĽnie
    0.06
    iliz
    0.06
    漫天
    0.06
    ä¼ļåıijçİ°
    0.06
    Activations Density 0.159%

    No Known Activations