© 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. 7256
    Prev
    Next
    INDEX
    Explanations

    also known, let G

    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
     "***
    -0.09
    AndWait
    -0.08
    iby
    -0.08
    kofen
    -0.08
    INGK
    -0.08
    -labelledby
    -0.07
    _starts
    -0.07
    TextNode
    -0.07
    turut
    -0.07
    pring
    -0.07
    POSITIVE LOGITS
    ‘
    0.09
     âĢ¦
    0.09
     ‘
    0.08
    âĢij
    0.08
    /
    0.07
    \n
    0.07
    âĢ¦âĢ¦
    0.07
    (\'
    0.07
    0.07
     ’
    0.06
    Activations Density 0.136%

    No Known Activations