© 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. 20833
    Prev
    Next
    INDEX
    Explanations

    breakdown or down

    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
    acman
    -0.09
    ihu
    -0.09
    orza
    -0.08
    prus
    -0.08
    å¿ĺæĢĢ
    -0.08
    ertz
    -0.08
    λάÏĩ
    -0.08
    kert
    -0.08
    icina
    -0.08
    atric
    -0.08
    POSITIVE LOGITS
    æĭĨ解
    0.09
     into
    0.08
    åĪĨ解
    0.08
    åĪ°å°¾
    0.07
     breakdown
    0.07
    into
    0.07
    ç»Ĩ
    0.07
    æĪIJä¸Ģ
    0.07
    æķ´ä¸ª
    0.06
    ings
    0.06
    Activations Density 0.008%

    No Known Activations