© 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. 8752
    Prev
    Next
    INDEX
    Explanations

    two times or repeated

    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
    è°ģèĥ½
    -0.06
    emi
    -0.06
    rap
    -0.06
    ipt
    -0.06
    пÑĤи
    -0.06
    Separ
    -0.06
    omy
    -0.06
    ans
    -0.06
    nom
    -0.06
    _place
    -0.06
    POSITIVE LOGITS
    å¤ļ次
    0.11
    两次
    0.10
    åĨįä¸ī
    0.10
     repeated
    0.10
     twice
    0.10
     дваждÑĭ
    0.10
    çļĦ两个
    0.10
    два
    0.09
    ä¸ī次
    0.09
    åĽĽæ¬¡
    0.09
    Activations Density 0.063%

    No Known Activations