© 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. 43348
    Prev
    Next
    INDEX
    Explanations

    Russian characters and UTF-8

    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
    ushman
    -0.07
    tro
    -0.07
    çģ«çļĦ
    -0.06
    è¿Ń
    -0.06
    oba
    -0.06
    quires
    -0.06
    TRO
    -0.06
    åĪ°åºķæĺ¯ä»Ģä¹Ī
    -0.06
    è§ģçĬ¶
    -0.06
     gleichen
    -0.06
    POSITIVE LOGITS
    ï¸İ
    0.07
    رات
    0.07
    èĢħæĺ¯
    0.07
    echt
    0.07
    anoia
    0.07
     {})
    0.07
    वल
    0.07
    èĢħ为
    0.07
    .styles
    0.07
    vertisement
    0.07
    Activations Density 0.003%

    No Known Activations