© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 62124
    Prev
    Next
    INDEX
    Explanations

    is positive or traditional

    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
    好å¤ļ
    -0.08
    rosse
    -0.08
    å¥½äºĽ
    -0.08
     thô
    -0.07
    PackageManager
    -0.07
    osta
    -0.07
     usually
    -0.07
    attie
    -0.07
    åħ¶ä»ĸåªĴä½ĵ
    -0.07
    DataStream
    -0.07
    POSITIVE LOGITS
    æİ¥åıĹ
    0.07
    лÑij
    0.07
    úr
    0.07
    NullOr
    0.07
     simply
    0.06
    ES
    0.06
    Sq
    0.06
    iche
    0.06
     celo
    0.06
    åįĺç´Ķ
    0.06
    Activations Density 0.002%

    No Known Activations