© 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. 62470
    Prev
    Next
    INDEX
    Explanations

    correct affiliation

    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
    ActivityResult
    -0.08
    ActionResult
    -0.08
    IVA
    -0.08
    ignano
    -0.07
    ceau
    -0.07
    ç»Ī
    -0.07
    ết
    -0.07
    è¿Ļç±»
    -0.07
    oces
    -0.07
     reverse
    -0.07
    POSITIVE LOGITS
    Ŀ
    0.08
     explicit
    0.07
     ëªħìĭľ
    0.07
    cls
    0.07
    íĮħ
    0.07
     specifying
    0.07
    æijĩæijĩ
    0.07
     explicitly
    0.07
    oyer
    0.07
    éĻIJå®ļ
    0.07
    Activations Density 0.005%

    No Known Activations