© 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. 3766
    Prev
    Next
    INDEX
    Explanations

    math or code block terminators

    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
    Ø©
    -0.16
    ness
    -0.14
    ation
    -0.13
    ity
    -0.11
    ities
    -0.08
    ение
    -0.08
    ITY
    -0.08
    Âł
    -0.08
    entication
    -0.08
    sam
    -0.07
    POSITIVE LOGITS
    zelfde
    0.10
    俱ä¹IJéĥ¨
    0.10
    æĸ°åĬłåĿ¡
    0.09
    缸è¾ħ缸æĪIJ
    0.09
    rastructure
    0.08
    à¸Ħà¹Į
    0.08
    bamos
    0.08
    utral
    0.08
    ufer
    0.08
    ransition
    0.08
    Activations Density 0.001%

    No Known Activations