© 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. 61539
    Prev
    Next
    INDEX
    Explanations

    repeated uppercase letters and symbols

    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
     Pend
    -0.07
    -0.06
    æīĭçĶµ
    -0.06
    inov
    -0.06
    ç«ĭåį³ä¸ĭè½½
    -0.06
    kut
    -0.06
    ÃĬM
    -0.06
     elev
    -0.06
    stå
    -0.06
    kien
    -0.06
    POSITIVE LOGITS
    uten
    0.08
    estroy
    0.08
    åįĥåįĥ
    0.07
    odash
    0.07
    ë¡ľìļ´
    0.07
    å¹³éĺ³
    0.07
    itals
    0.07
    abic
    0.07
    iales
    0.07
    ength
    0.07
    Activations Density 0.038%

    No Known Activations