© 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. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 3657
    Prev
    Next
    INDEX
    Explanations

    detail, click, follow

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/olmo-3-saes/olmo-3-1025-7b
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lim
    -0.09
    .pub
    -0.09
    atsu
    -0.09
     stark
    -0.08
     eer
    -0.08
     bekan
    -0.08
    lap
    -0.08
    UIT
    -0.08
    iere
    -0.08
    keywords
    -0.08
    POSITIVE LOGITS
     deeper
    0.16
     fuller
    0.16
     underlying
    0.14
     further
    0.13
     supplementary
    0.13
     follow
    0.12
     detailed
    0.12
     full
    0.12
     detail
    0.12
     elsewhere
    0.12
    Activations Density 0.474%

    No Known Activations