© 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. 32906
    Prev
    Next
    INDEX
    Explanations

    set of numbers or elements

    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
     ÄijáºŃm
    -0.08
    essler
    -0.08
    aan
    -0.07
    åķĨçļĦ
    -0.07
    aque
    -0.07
    haj
    -0.07
    lust
    -0.07
    alian
    -0.07
    chal
    -0.07
    Ïĥμ
    -0.07
    POSITIVE LOGITS
    ?,?,
    0.08
    jenigen
    0.07
    ories
    0.07
    _='
    0.07
    tons
    0.07
    ãģ¹ãģį
    0.07
     ÑģообÑīа
    0.06
    ä¸Ģå®ļä¸įè¦ģ
    0.06
    one
    0.06
    ège
    0.06
    Activations Density 0.024%

    No Known Activations