© 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. 55370
    Prev
    Next
    INDEX
    Explanations

    register, type, system, core, std, crate

    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
    pii
    -0.10
     affiliates
    -0.09
     gre
    -0.09
    avi
    -0.08
    ifu
    -0.08
     Laz
    -0.08
     Worse
    -0.08
     sass
    -0.08
    ensis
    -0.08
    sizeof
    -0.08
    POSITIVE LOGITS
    àµį
    0.08
     Modal
    0.08
     stand
    0.08
     inn
    0.08
    esp
    0.07
    iest
    0.07
     Abdul
    0.07
     straight
    0.07
     dirty
    0.07
    )i
    0.07
    Activations Density 0.003%

    No Known Activations