© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 9226
    Prev
    Next
    INDEX
    Explanations

    manifestation or expression

    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
    duc
    -0.07
    åįĬæĻĮ
    -0.07
    True
    -0.06
    bara
    -0.06
    zal
    -0.06
     Fond
    -0.06
    æĶ¾åľ¨é¦ĸä½į
    -0.06
    rollo
    -0.06
    <size
    -0.06
    åįĹå±±
    -0.06
    POSITIVE LOGITS
     manifestation
    0.14
     manifestations
    0.12
    表çİ°å½¢å¼ı
    0.11
    Manifest
    0.10
     manifested
    0.10
    manifest
    0.10
     Manifest
    0.10
    _manifest
    0.09
    ä½ĵçİ°
    0.09
     manifest
    0.09
    Activations Density 0.060%

    No Known Activations