© 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. 39696
    Prev
    Next
    INDEX
    Explanations

    citations after years (XXXX)

    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
     Zuk
    -0.07
    mens
    -0.07
    oug
    -0.07
    ublic
    -0.07
     Soo
    -0.07
    uzzle
    -0.06
    ookie
    -0.06
    aios
    -0.06
    enny
    -0.06
    èŀįèŀį
    -0.06
    POSITIVE LOGITS
    å³¥
    0.07
    éĨĩ
    0.07
    Âł
    0.07
    å¾ĢæľŁåĽŀ顾
    0.07
    bard
    0.06
    LLLL
    0.06
    ìĪ
    0.06
    kah
    0.06
    ä¸į该
    0.06
    awe
    0.06
    Activations Density 0.050%

    No Known Activations