© 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. 54999
    Prev
    Next
    INDEX
    Explanations

    explain

    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
    ibs
    -0.08
    _finder
    -0.08
    opin
    -0.08
    bris
    -0.08
    ä¸ĵæłıæĶ¶å½ķ该åĨħ容
    -0.07
    stum
    -0.07
    ovol
    -0.07
    aket
    -0.07
    年头
    -0.07
    _printer
    -0.07
    POSITIVE LOGITS
    ä¸Ģä¸ĭåŃIJ
    0.07
    ä¸Ģä¸ĭ
    0.07
     concept
    0.07
    ify
    0.07
    urut
    0.06
    why
    0.06
    ä¸Ģä¸ĭåIJ§
    0.06
     ho
    0.06
    è¶Ĭ
    0.06
    æĻ¦
    0.06
    Activations Density 0.013%

    No Known Activations