© 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. 32926
    Prev
    Next
    INDEX
    Explanations

    Greek letters and formulas

    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
    èī¯
    -0.08
    à¸ŀาà¸Ļ
    -0.08
    eht
    -0.08
    queta
    -0.08
    å¤ĸæķĻ
    -0.08
    cket
    -0.07
    IEW
    -0.07
    .music
    -0.07
    å¼ı设计
    -0.07
    owie
    -0.07
    POSITIVE LOGITS
    oyer
    0.07
    astre
    0.06
    çļĦåŁºæľ¬è¦ģæ±Ĥ
    0.06
    å®Īåľ¨
    0.06
    ues
    0.06
    ÙĨا
    0.06
    èĩªåıij
    0.06
    appa
    0.06
    app
    0.06
    ÑĪÑĮ
    0.06
    Activations Density 0.005%

    No Known Activations