© 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. 47392
    Prev
    Next
    INDEX
    Explanations

    country codes or language names

    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
    éģį
    -0.07
    ä»Ĭ天çļĦ
    -0.06
    æĬĦ
    -0.06
    mgr
    -0.06
    -0.06
    æīĢåģļçļĦ
    -0.06
    >this
    -0.06
    -0.06
    anc
    -0.06
    大çļĦ
    -0.06
    POSITIVE LOGITS
    åħ°çī¹
    0.08
    isal
    0.08
    uden
    0.08
    ÑĢей
    0.07
    åijĨäºĨ
    0.07
    gede
    0.07
    olak
    0.07
     getr
    0.07
    _pref
    0.07
    intele
    0.07
    Activations Density 0.338%

    No Known Activations