© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 59987
    Prev
    Next
    INDEX
    Explanations

    progeny, inheritance, generation

    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
    Negative Logits
    witz
    -0.07
    ÙĨاس
    -0.07
    ×Ĺת
    -0.07
    _remain
    -0.06
    лиÑĢÑĥ
    -0.06
    gang
    -0.06
    åĿ¦
    -0.06
    è¡¡
    -0.06
    ä¸İæŶ
    -0.06
    娲
    -0.06
    POSITIVE LOGITS
    ozy
    0.09
     generation
    0.08
    å°Ŀ
    0.08
    jedn
    0.08
     generación
    0.07
    /generated
    0.07
     inherits
    0.07
    ´Ģ
    0.07
     déb
    0.07
    veil
    0.07
    Activations Density 0.002%

    No Known Activations