© 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. 2063
    Prev
    Next
    INDEX
    Explanations

    technical language

    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
    ='{$
    -0.22
    daq
    -0.21
    ognito
    -0.21
    acin
    -0.20
    [:,:
    -0.20
    <ActionResult
    -0.20
    locker
    -0.19
    ocos
    -0.19
    anka
    -0.19
    ambio
    -0.19
    POSITIVE LOGITS
    æĿ¥çľĭçľĭåIJ§
    0.25
    ippines
    0.21
    contri
    0.21
    eterangan
    0.21
    upos
    0.20
    toupper
    0.20
    ournemouth
    0.20
     goût
    0.20
    specifier
    0.20
    stery
    0.20
    Activations Density 0.003%

    No Known Activations