© 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. 2083
    Prev
    Next
    INDEX
    Explanations

    code context

    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
    blr
    -0.23
    -Compatible
    -0.23
    çī¹æľĹ
    -0.23
    esktop
    -0.22
    -Token
    -0.22
    chestra
    -0.22
    ÃŃses
    -0.22
    agenta
    -0.22
    )application
    -0.21
    lke
    -0.21
    POSITIVE LOGITS
     offsetof
    0.22
    vably
    0.21
    access
    0.21
    说åĩº
    0.20
    渣
    0.20
     IReadOnly
    0.20
    offsetof
    0.20
     Uncomment
    0.20
    /raw
    0.19
    èµ·
    0.19
    Activations Density 0.147%

    No Known Activations