© 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. 1362
    Prev
    Next
    INDEX
    Explanations

    Yet yet

    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
    ught
    -0.09
    -quarters
    -0.07
    Ñıд
    -0.07
     zwar
    -0.07
    ussen
    -0.07
    aliza
    -0.07
    ÛĮÙĩ
    -0.07
    hawk
    -0.07
    Äįius
    -0.07
    åijĺ
    -0.07
    POSITIVE LOGITS
    ness
    0.10
     Äijặn
    0.10
    minster
    0.10
    ledge
    0.09
    ters
    0.09
    zelfde
    0.09
    اÙħØ©
    0.08
    åģıåģı
    0.08
    ÙĬÙĨØ©
    0.08
    UDE
    0.08
    Activations Density 0.015%

    No Known Activations