© 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. 46880
    Prev
    Next
    INDEX
    Explanations

    sequences after parentheses

    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
    以对
    -0.07
     seterusnya
    -0.07
    ons
    -0.07
    antung
    -0.07
    é¾Ħ
    -0.07
    yno
    -0.06
    udir
    -0.06
    andas
    -0.06
    nich
    -0.06
     Corey
    -0.06
    POSITIVE LOGITS
    envir
    0.07
    .Sequence
    0.07
    OTP
    0.07
    å¸Ń
    0.07
    æĸ
    0.07
     Generic
    0.07
    stdarg
    0.06
    åıĭ
    0.06
    éħ¬
    0.06
     generic
    0.06
    Activations Density 0.045%

    No Known Activations