© 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. 11513
    Prev
    Next
    INDEX
    Explanations

    programming, technical terms, or domain identifiers

    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
    ii
    -0.06
    侧
    -0.06
    inv
    -0.06
    ien
    -0.06
    anton
    -0.06
    çİĭæĸĩ
    -0.06
    çİ
    -0.06
     astr
    -0.06
    umbo
    -0.06
    åij½
    -0.06
    POSITIVE LOGITS
    å°±éĢģ
    0.08
    éĶ¦æ¶Ľ
    0.08
    ériel
    0.08
    foon
    0.08
    åĽ¾çŃī
    0.07
     statistik
    0.07
    æĥħåĨµçŃī
    0.07
    utz
    0.07
    Ñħодов
    0.07
    áĥĶáĥ¡
    0.07
    Activations Density 0.011%

    No Known Activations