© 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. 11082
    Prev
    Next
    INDEX
    Explanations

    comments after specific characters

    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
    ation
    -0.10
    ção
    -0.08
    ample
    -0.07
    ationen
    -0.07
    icit
    -0.07
     ↵            ↵
    -0.07
    iona
    -0.07
    ientos
    -0.07
    iban
    -0.07
    ение
    -0.07
    POSITIVE LOGITS
    suite
    0.09
    俱ä¹IJéĥ¨
    0.08
    sst
    0.08
    estone
    0.08
    à¸Ħà¹īา
    0.07
    ر
    0.07
    deaux
    0.07
    leÅŁtir
    0.07
    spre
    0.07
    nya
    0.07
    Activations Density 0.072%

    No Known Activations