© 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. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 525
    Prev
    Next
    INDEX
    Explanations

    word endings

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/qwen2.5-7B-it-layer-20-saes/pile/matryoshka/k-100
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ok
    -0.22
     )*
    -0.20
    hal
    -0.20
    pressão
    -0.19
    _NC
    -0.19
     íĨµíķĺìŬ
    -0.19
    RESSED
    -0.19
     OG
    -0.18
    å°ı康社ä¼ļ
    -0.18
    èħ¹
    -0.18
    POSITIVE LOGITS
    :CGRect
    0.26
    echa
    0.23
    æµĴ
    0.22
    onent
    0.22
    iginal
    0.22
    ÄĻb
    0.21
    iais
    0.21
    lâ
    0.21
    uters
    0.20
    )((((
    0.20
    Activations Density 0.010%

    No Known Activations