© 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. 908
    Prev
    Next
    INDEX
    Explanations

    sacred texts like Purana

    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
    两æĢ§
    -0.07
    berat
    -0.07
    appers
    -0.07
     Jedi
    -0.07
    å¥ł
    -0.06
    æĦıæĸĻ
    -0.06
    对å¸Ĥåľº
    -0.06
    Iterable
    -0.06
     Py
    -0.06
     koal
    -0.06
    POSITIVE LOGITS
    agenta
    0.08
    _mgr
    0.08
    æħĪ
    0.08
    urm
    0.08
    åı£çº¢
    0.08
    ENDOR
    0.07
    å¿µä½Ľ
    0.07
    tto
    0.07
    endorf
    0.07
    /tags
    0.07
    Activations Density 0.010%

    No Known Activations