© 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. 15343
    Prev
    Next
    INDEX
    Explanations

    lists with colons and specific following words

    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
    ä¸ĭæīĭ
    -0.07
    éħ
    -0.07
    ütz
    -0.06
    wijk
    -0.06
     gewe
    -0.06
     ÅŁekl
    -0.06
    à°ĸ
    -0.06
     intime
    -0.06
    çļĦè¿ĺæľī
    -0.06
    áīł
    -0.06
    POSITIVE LOGITS
    åħ³äºİ
    0.08
    ustra
    0.08
    åį³åĪ°
    0.08
    åĴĮ第
    0.08
    оÑģÑĤо
    0.07
    åĨħ容æĺ¯
    0.07
    lon
    0.07
    vest
    0.07
    asher
    0.07
    å¦ŀ
    0.07
    Activations Density 0.121%

    No Known Activations