© 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. 256
    Prev
    Next
    INDEX
    Explanations

    LaTeX typesetting

    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
     Según
    -0.25
     deltaTime
    -0.22
     gameTime
    -0.21
     handguns
    -0.21
     Baghd
    -0.21
     vö
    -0.21
     HuffPost
    -0.20
     Mediterr
    -0.20
    \:
    -0.20
     REUTERS
    -0.20
    POSITIVE LOGITS
    ãİľ
    0.23
     LaTeX
    0.22
    .tex
    0.21
    çĽ¸å¹²
    0.21
    ByUrl
    0.21
     fontsize
    0.21
    é»ijæģ¶
    0.20
    TeX
    0.20
     DeepCopy
    0.20
     BroadcastReceiver
    0.20
    Activations Density 0.468%

    No Known Activations