© 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. 17075
    Prev
    Next
    INDEX
    Explanations

    "ask me in five years' time"

    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
    prost
    -0.08
    noop
    -0.08
    åį¿
    -0.07
    idou
    -0.07
    æī£çķĻ
    -0.07
    æ¯Ķäºļ
    -0.07
    borough
    -0.07
    èݱ德
    -0.07
    纳æĸ¯
    -0.07
    uppe
    -0.07
    POSITIVE LOGITS
    æºī
    0.08
    çİ°åľ¨çľĭæĿ¥
    0.07
    å¾Ħ
    0.07
    attes
    0.06
    èĢĮå¦Ĥä»Ĭ
    0.06
     bart
    0.06
    æł¼å±Ģ
    0.06
    ä½łè¿ĺåľ¨
    0.06
     mentality
    0.06
    èĢĮåıĪ
    0.06
    Activations Density 0.007%

    No Known Activations