© 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. 2287
    Prev
    Next
    INDEX
    Explanations

    job titles, roles

    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
     whiteColor
    -0.23
    èħ§
    -0.20
    :numel
    -0.20
    [email
    -0.19
    æĿª
    -0.19
     later
    -0.19
    getMock
    -0.19
    lard
    -0.18
     extr
    -0.18
    .synthetic
    -0.18
    POSITIVE LOGITS
     }}>{
    0.23
     Aires
    0.22
    ]bool
    0.20
    ä»»æķĻ
    0.20
    'field
    0.20
     bénéficie
    0.20
    ="">č↵
    0.19
     employed
    0.19
    æĭľå¸ĪåѦ
    0.19
    usher
    0.19
    Activations Density 0.626%

    No Known Activations