© 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. 8627
    Prev
    Next
    INDEX
    Explanations

    citation markers

    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
    ำ
    -0.09
    reden
    -0.08
    abbo
    -0.08
    abah
    -0.08
    çĸ«æĥħéĺ²æݧåĴĮ
    -0.08
     reci
    -0.08
    kti
    -0.08
    ordo
    -0.07
    iman
    -0.07
    æŀģ端
    -0.07
    POSITIVE LOGITS
    ist
    0.06
    ub
    0.06
    Un
    0.06
    isle
    0.06
    bk
    0.06
    ÙĪÙĨÙĩ
    0.06
    1
    0.06
    athe
    0.06
    éĻĪå°ı
    0.06
    ende
    0.06
    Activations Density 0.113%

    No Known Activations