© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 4065
    Prev
    Next
    INDEX
    Explanations

    characters and digits

    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
    ottes
    -0.08
    riad
    -0.07
    aign
    -0.07
    atea
    -0.06
    æİ¥åľ°æ°Ķ
    -0.06
    ahu
    -0.06
    earth
    -0.06
    好åѦçĶŁ
    -0.06
    ìĸ´ìĦľ
    -0.06
    QÄIJ
    -0.06
    POSITIVE LOGITS
    eneg
    0.08
    æŁ»
    0.07
    循
    0.07
    åĮ
    0.07
    ä¸į移
    0.07
    ydd
    0.07
    éĽĢ
    0.06
    ãħ
    0.06
    aname
    0.06
    åį
    0.06
    Activations Density 0.011%

    No Known Activations