© 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. 25701
    Prev
    Next
    INDEX
    Explanations

    experience

    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
    кÑĥда
    -0.09
    ìį¨
    -0.08
    ination
    -0.08
    arians
    -0.08
    aked
    -0.08
     íĸ¥íķľ
    -0.08
     kepentingan
    -0.08
    shire
    -0.08
    erial
    -0.08
    Referensi
    -0.07
    POSITIVE LOGITS
     nghiá»ĩm
    0.09
    encing
    0.08
    neh
    0.08
    åĪ°çļĦ
    0.08
    tual
    0.07
    uale
    0.07
    perience
    0.07
    entially
    0.07
    eur
    0.07
     firsthand
    0.07
    Activations Density 0.041%

    No Known Activations