© 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. 4867
    Prev
    Next
    INDEX
    Explanations

    closing parenthesis followed by other tokens

    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
    å°Ķé¡¿
    -0.07
    re
    -0.07
    -0.07
     Nett
    -0.07
     net
    -0.06
     Net
    -0.06
     Lut
    -0.06
    ro
    -0.06
    é¾ĻçļĦ
    -0.06
    ly
    -0.06
    POSITIVE LOGITS
    ä½ľåĵģä»ĭç»į
    0.09
    ãģ©ãģĵãĤį
    0.09
    weiler
    0.09
    ubil
    0.09
    amiliar
    0.08
    产
    0.08
    dorf
    0.08
    ehme
    0.08
     KeyValuePair
    0.08
    usize
    0.08
    Activations Density 0.006%

    No Known Activations