© 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. 13227
    Prev
    Next
    INDEX
    Explanations

    proper noun places and origins

    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
     Roberts
    -0.07
    iefe
    -0.07
    /functions
    -0.06
    eid
    -0.06
    reen
    -0.06
    æľįçļĦ
    -0.06
    æķĻèĤ²å¼ķ导
    -0.06
    _pref
    -0.06
    /helpers
    -0.06
    otte
    -0.06
    POSITIVE LOGITS
    0.08
    otas
    0.07
     ($.
    0.07
    Times
    0.07
    ovolta
    0.07
    å±ķå¼Ģåħ¨æĸĩ
    0.07
    ä¼Ĺ
    0.07
     obv
    0.06
     rzecz
    0.06
    ulatory
    0.06
    Activations Density 0.015%

    No Known Activations