© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 16898
    Prev
    Next
    INDEX
    Explanations

    equal, level, or drawn comparisons

    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
    éĩĩ
    -0.08
     unint
    -0.08
    æİ¡
    -0.08
    apis
    -0.08
    ophil
    -0.07
    gaard
    -0.07
    èģļæ°¨
    -0.07
    vern
    -0.07
    æ¸
    -0.07
    à¸Ĺะ
    -0.07
    POSITIVE LOGITS
    aner
    0.07
    rand
    0.07
    aze
    0.07
    uhr
    0.07
    _VIRTUAL
    0.07
    Reserved
    0.07
    æµ·çıł
    0.06
    och
    0.06
    azes
    0.06
    azing
    0.06
    Activations Density 0.002%

    No Known Activations