© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 12067
    Prev
    Next
    INDEX
    Explanations

    javascript exports default function

    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
    ted
    -0.07
    诱
    -0.07
    å¼ĥ
    -0.07
    esak
    -0.07
    odr
    -0.07
    顺å¿ĥ
    -0.07
    çĥĤ漫
    -0.07
     Ting
    -0.07
    ei
    -0.07
    çĶ»å»Ĭ
    -0.07
    POSITIVE LOGITS
    æķ´
    0.07
    polis
    0.07
    åĩı
    0.07
    人家
    0.07
    âĨĵâĨĵ
    0.07
    giv
    0.06
    uhl
    0.06
    ajer
    0.06
    lasses
    0.06
     combust
    0.06
    Activations Density 0.006%

    No Known Activations