© 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
    2. Olmo-3-1025-7B
    3. 16-RES-MATRYOSHKA-65K
    4. 58244
    Prev
    Next
    INDEX
    Explanations

    font size or dimensions in px/pt

    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
    illion
    -0.11
     neu
    -0.10
    ich
    -0.09
    oen
    -0.09
     Gazette
    -0.09
     tier
    -0.09
     utilities
    -0.08
     ANSI
    -0.08
     Utilities
    -0.08
     richer
    -0.07
    POSITIVE LOGITS
    ]:↵↵↵
    0.09
    ');↵↵↵↵
    0.09
    ilate
    0.09
     intercepted
    0.09
    otec
    0.09
    ateg
    0.09
    .nav
    0.09
    abus
    0.08
     Sunshine
    0.08
    @student
    0.08
    Activations Density 0.003%

    No Known Activations