© 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. 58917
    Prev
    Next
    INDEX
    Explanations

    technical prefixes and suffixes

    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
    -0.07
    æīĭ
    -0.07
    ä½Ĩä¸įéĻIJäºİ
    -0.06
    å¤ĸ
    -0.06
    åĵİ
    -0.05
    Âł
    -0.05
     sc
    -0.05
    ı
    -0.05
    ç¨ĭ度ä¸Ĭ
    -0.05
    ç®Ń
    -0.05
    POSITIVE LOGITS
    estig
    0.10
    geführ
    0.10
    ä½ľåĪĻ
    0.09
    écu
    0.08
    ç«ĭåį³ä¸ĭè½½
    0.08
    olÃŃ
    0.08
    лика
    0.08
    à¹Īำ
    0.08
    ÃŃlico
    0.08
    нÑĸка
    0.08
    Activations Density 0.062%

    No Known Activations