© 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. 608
    Prev
    Next
    INDEX
    Explanations

    a type

    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
    <|box_end|>
    -0.09
    ConverterFactory
    -0.09
    forcer
    -0.08
    azgo
    -0.08
     pakken
    -0.08
    ìĿ´ì¦Ī
    -0.08
     ÎŃξ
    -0.08
     Garner
    -0.08
     оÑĩев
    -0.08
    ä½ķ为
    -0.08
    POSITIVE LOGITS
     distinguished
    0.07
     whose
    0.06
    a
    0.06
    ç»Ļ人ä¸Ģç§į
    0.06
     set
    0.06
    uyer
    0.06
    1
    0.06
    å½ĵåħ¶
    0.06
    amer
    0.06
     specializing
    0.06
    Activations Density 0.066%

    No Known Activations