© 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. 56655
    Prev
    Next
    INDEX
    Explanations

    .com suffix

    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
     labour
    -0.07
    @c
    -0.07
     exp
    -0.07
    rolled
    -0.06
    anks
    -0.06
     labor
    -0.06
    #c
    -0.06
    egen
    -0.06
    稼
    -0.06
    .framework
    -0.06
    POSITIVE LOGITS
    agia
    0.10
    Ñĥже
    0.08
    tryk
    0.08
    try
    0.07
    ael
    0.07
    yntax
    0.07
    uÄį
    0.07
    peg
    0.07
    agation
    0.07
    aye
    0.07
    Activations Density 0.050%

    No Known Activations