© 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. 12807
    Prev
    Next
    INDEX
    Explanations

    scrolling, parking, current, index, investigation, animation, bug, corruption

    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
    ')['
    -0.08
    ablish
    -0.07
    жеÑĤ
    -0.06
    edException
    -0.06
    SPAN
    -0.06
    ewan
    -0.06
    uppen
    -0.06
    bonne
    -0.06
    bli
    -0.06
    TURE
    -0.06
    POSITIVE LOGITS
     ës
    0.08
    ä¸įåĢĴ
    0.07
    对äºİæĪij们
    0.07
    aimer
    0.07
    âĢŀ
    0.06
    ekh
    0.06
    让广大
    0.06
    like
    0.06
    кза
    0.06
    imir
    0.06
    Activations Density 0.105%

    No Known Activations