© 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. 49811
    Prev
    Next
    INDEX
    Explanations

    numbers followed by slashes

    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
    iby
    -0.07
    åį°ç¬¬
    -0.07
    udded
    -0.07
    èĢĮ以
    -0.07
    ÙĦÙĪد
    -0.07
    è¦ģæ±ĤåIJĦ
    -0.06
    íĹĮ
    -0.06
    ibus
    -0.06
    家常
    -0.06
    æĹºéĵº
    -0.06
    POSITIVE LOGITS
    wick
    0.09
    essler
    0.08
    anced
    0.08
    å
    0.07
    pros
    0.07
    ancel
    0.07
    RIES
    0.07
    atsu
    0.07
    imony
    0.07
    è°ħ
    0.07
    Activations Density 0.002%

    No Known Activations