© 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. 16112
    Prev
    Next
    INDEX
    Explanations

    numbers and years

    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
    erialized
    -0.09
    /mail
    -0.09
    å¼ı
    -0.09
    åĹĵ
    -0.09
    annes
    -0.08
    å¼ıä¸Ń
    -0.08
    æł¸å¿ĥæĬĢæľ¯
    -0.07
    \core
    -0.07
    inned
    -0.07
    acus
    -0.07
    POSITIVE LOGITS
     rare
    0.09
     rar
    0.09
    éļ¾å¾Ĺ
    0.08
    丽èİİ
    0.07
    rare
    0.07
     rarity
    0.07
     sparse
    0.07
    hm
    0.07
    regen
    0.07
    ç¨Ģæľī
    0.07
    Activations Density 1.303%

    No Known Activations