© 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. 843
    Prev
    Next
    INDEX
    Explanations

    original main branch

    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
     privilegi
    -0.08
    ehu
    -0.07
    schluss
    -0.07
    _INLINE
    -0.07
    òng
    -0.06
    ä¸ĵå±ŀ
    -0.06
     privilégi
    -0.06
    enne
    -0.06
    enis
    -0.06
    ogle
    -0.06
    POSITIVE LOGITS
    /original
    0.13
     original
    0.09
    åİŁ
    0.09
     Original
    0.08
     underlying
    0.08
    original
    0.08
     originales
    0.08
    åİŁå®ļ
    0.08
     اÙĦأصÙĦÙĬ
    0.08
    åİŁä½ľ
    0.08
    Activations Density 0.119%

    No Known Activations