© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 2525
    Prev
    Next
    INDEX
    Explanations

    php namespace declarations

    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
     Gaz
    -0.09
    ↵
    -0.06
    tdown
    -0.06
    zzle
    -0.06
    漪
    -0.06
     mist
    -0.05
    -response
    -0.05
    Âł
    -0.05
     Mon
    -0.05
     Rip
    -0.05
    POSITIVE LOGITS
     Сод
    0.09
    .pkg
    0.09
     menyar
    0.08
    psilon
    0.08
    ilenames
    0.08
    reater
    0.08
    åľ¨çº¿çķĻè¨Ģ
    0.08
    è¿Ļæĺ¯æĪijçļĦ
    0.08
    _DLL
    0.08
    اÙĥ
    0.08
    Activations Density 0.009%

    No Known Activations