© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 3255
    Prev
    Next
    INDEX
    Explanations

    technical or scientific 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
    avel
    -0.22
    (parseFloat
    -0.22
    -ie
    -0.21
    .NoArgsConstructor
    -0.21
    )init
    -0.19
    lasting
    -0.19
     redistributed
    -0.19
    );↵↵↵↵↵
    -0.19
    :".$
    -0.18
    Vectorizer
    -0.18
    POSITIVE LOGITS
     IonicPage
    0.27
    AGMA
    0.24
    éĩįè¦ģåĽłç´ł
    0.23
    abbix
    0.22
    ampions
    0.20
    czÄĻ
    0.19
     gameTime
    0.19
    åĭ
    0.19
     strokeWidth
    0.19
    è§
    0.19
    Activations Density 0.001%

    No Known Activations