© 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. 1524
    Prev
    Next
    INDEX
    Explanations

    proper nouns

    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
    opportunitÃł
    -0.26
     Wrest
    -0.25
    |array
    -0.23
     ofApp
    -0.22
     jihadists
    -0.22
     ÑģенÑĤ
    -0.20
     jihadist
    -0.20
     INCIDENT
    -0.20
    ecided
    -0.20
     malaysia
    -0.19
    POSITIVE LOGITS
    âĩIJ
    0.22
     cornerback
    0.21
     Am
    0.20
    prowad
    0.19
    luet
    0.18
    <tbody
    0.18
    >↵↵↵↵↵
    0.18
    opoly
    0.18
    orts
    0.18
    _HOOK
    0.17
    Activations Density 0.009%

    No Known Activations