© 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. 421
    Prev
    Next
    INDEX
    Explanations

    code or technical terms

    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
    ueling
    -0.20
    urope
    -0.20
    IR
    -0.20
    ]|[
    -0.19
     Sach
    -0.19
    /problems
    -0.19
    /DTD
    -0.19
     سبØŃاÙĨÙĩ
    -0.19
    .ua
    -0.19
     slik
    -0.19
    POSITIVE LOGITS
    oenix
    0.22
    åıĻ
    0.21
    nyder
    0.21
     @}
    0.20
     cellForRowAt
    0.20
    folio
    0.20
    ruc
    0.20
    rus
    0.20
    reducers
    0.19
    QUIRED
    0.19
    Activations Density 0.001%

    No Known Activations