© 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. 58595
    Prev
    Next
    INDEX
    Explanations

    sum and squared

    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
    è¿ĶåĽŀ顶éĥ¨
    -0.06
    ceed
    -0.06
    çļĻ
    -0.06
    å°ı鹿
    -0.06
    verkehrs
    -0.06
    searchModel
    -0.06
    ault
    -0.06
    åı¥åı¥
    -0.06
     fragile
    -0.06
    igu
    -0.06
    POSITIVE LOGITS
    Squared
    0.08
     squared
    0.08
    mul
    0.08
    _PAIR
    0.08
    以ä¾Ĩ
    0.07
     squares
    0.07
    wal
    0.07
    kar
    0.07
    éĺ¶å±Ĥ
    0.07
    zie
    0.07
    Activations Density 0.010%

    No Known Activations