© 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. 34786
    Prev
    Next
    INDEX
    Explanations

    quotation marks

    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
    INGER
    -0.07
    ινÏĮ
    -0.07
    ijn
    -0.07
    ached
    -0.07
     impeccable
    -0.07
    èIJİéĿ¡
    -0.07
    otle
    -0.07
    esito
    -0.07
    åħ·æľīéĩįè¦ģçļĦ
    -0.07
    æīĢæĢĿ
    -0.07
    POSITIVE LOGITS
     "
    0.09
     “
    0.08
    Ľ
    0.08
    "-
    0.08
    “
    0.07
    åIJİæĦŁ
    0.07
    ãģªãģĮãĤī
    0.07
    åįĬ个
    0.07
    rella
    0.07
    æīĵäºĨ
    0.06
    Activations Density 0.100%

    No Known Activations