© 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. 4355
    Prev
    Next
    INDEX
    Explanations

    percentile curves

    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
    交代
    -0.08
    æĿĤ
    -0.07
     memcmp
    -0.07
     Penc
    -0.07
    _checks
    -0.07
     seams
    -0.07
    æĦıè¯Ĩ
    -0.07
    亲
    -0.06
    é£ŀ
    -0.06
    rox
    -0.06
    POSITIVE LOGITS
    mania
    0.08
    ä¹ĭé«ĺ
    0.08
    对åºĶçļĦ
    0.07
    icone
    0.07
     percentile
    0.07
     corresponding
    0.07
    éŃĦ
    0.07
    anit
    0.06
    大ç¥ŀ
    0.06
    缸åºĶ
    0.06
    Activations Density 0.001%

    No Known Activations