© 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. 62359
    Prev
    Next
    INDEX
    Explanations

    code prefixes and suffixes

    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
    via
    -0.07
     via
    -0.06
    sel
    -0.06
    åħ¬åı¸åıijå±ķ
    -0.06
    ouver
    -0.06
    last
    -0.06
    iesel
    -0.06
    åıĺæĽ´åIJİ
    -0.06
    iek
    -0.06
     trữ
    -0.06
    POSITIVE LOGITS
    äºļçī¹
    0.08
    æľĪä¾Ľ
    0.07
    ÏĦεÏį
    0.07
    çĭĹä»Ķ
    0.07
    ioned
    0.07
    çªĿ
    0.07
    .Generation
    0.07
    ahari
    0.07
    IED
    0.07
    isko
    0.07
    Activations Density 0.004%

    No Known Activations