© 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. 15069
    Prev
    Next
    INDEX
    Explanations

    physical dimensions

    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
    éģ¨
    -0.09
    ucho
    -0.08
    ottes
    -0.08
    åIJĮèĪŁ
    -0.08
     Vorm
    -0.08
    jsc
    -0.07
    mega
    -0.07
    /from
    -0.07
    lopen
    -0.07
    iros
    -0.07
    POSITIVE LOGITS
    _dirty
    0.07
    ôn
    0.07
    -League
    0.06
    elde
    0.06
    åİŁæľ¬
    0.06
    åIJĪæł¼è¯ģ
    0.06
    设为
    0.06
    ims
    0.06
    udy
    0.06
     Gin
    0.06
    Activations Density 0.041%

    No Known Activations