© 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. 1962
    Prev
    Next
    INDEX
    Explanations

    character separators

    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
    æŃ»
    -0.07
    -0.07
    azit
    -0.07
    ynos
    -0.07
    ynet
    -0.07
    ynam
    -0.07
    ervas
    -0.07
    è½»æĺĵ
    -0.07
    ntag
    -0.07
    æ®Ĩ
    -0.07
    POSITIVE LOGITS
    λε
    0.08
    ัว
    0.07
    emain
    0.07
     Reve
    0.07
    thed
    0.07
    ond
    0.07
    ieme
    0.07
     Richardson
    0.07
    è°ģçŁ¥
    0.06
    à¹Ģà¸Ħ
    0.06
    Activations Density 0.001%

    No Known Activations