© 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. 42640
    Prev
    Next
    INDEX
    Explanations

    legal citations with asterisks

    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
    lay
    -0.09
    ucks
    -0.08
    essa
    -0.08
    们éĥ½
    -0.07
    utta
    -0.07
    utt
    -0.07
    .MODE
    -0.07
    æľīä¸Ģ款
    -0.07
    akh
    -0.07
    utsche
    -0.07
    POSITIVE LOGITS
    渤
    0.07
    Anim
    0.07
    æ´ŀ
    0.07
    æļ§
    0.07
    feh
    0.07
    inting
    0.07
    elked
    0.06
    ë¨
    0.06
    çݲçıij
    0.06
     rehe
    0.06
    Activations Density 0.040%

    No Known Activations