© 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. 44079
    Prev
    Next
    INDEX
    Explanations

    "us the", "doom 3"

    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
    à¹Īาà¸Ļ
    -0.07
    asics
    -0.07
    aight
    -0.07
    åĬłæĭ¿å¤§
    -0.07
    å°ıçľĭ
    -0.07
    .getTransaction
    -0.07
    ault
    -0.07
    家常èıľ
    -0.06
    輩
    -0.06
    enco
    -0.06
    POSITIVE LOGITS
    è¿ĩåİ»äºĨ
    0.06
    teri
    0.06
    ider
    0.06
    isters
    0.06
    éli
    0.06
    ly
    0.06
    àµĤ
    0.06
    rom
    0.06
    ator
    0.05
    uras
    0.05
    Activations Density 1.207%

    No Known Activations