© 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. 55197
    Prev
    Next
    INDEX
    Explanations

    "Intr" followed by "avit" or "SQL" followed by "Server"

    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
    igs
    -0.08
    igne
    -0.08
    inned
    -0.07
    ¤
    -0.07
    #__
    -0.07
     CreateTable
    -0.07
    ฯ
    -0.07
    صÙĪص
    -0.07
    çİ°å°±
    -0.07
    igid
    -0.07
    POSITIVE LOGITS
    zn
    0.07
    elon
    0.07
     ‘’
    0.06
    ãģ«ãģĬãģijãĤĭ
    0.06
    åijĬè¯īä½ł
    0.06
     ‘
    0.06
     âĢķ
    0.06
    yth
    0.06
    çļĦä¸ĸçķĮ
    0.06
    ostr
    0.06
    Activations Density 0.197%

    No Known Activations