© 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. 55087
    Prev
    Next
    INDEX
    Explanations

    document related suffixes

    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
    rus
    -0.09
    compan
    -0.08
    getic
    -0.08
    adar
    -0.08
    /ph
    -0.08
    ÑĤе
    -0.08
    bounding
    -0.08
    tones
    -0.07
    pen
    -0.07
     reclaim
    -0.07
    POSITIVE LOGITS
    ed
    0.14
    ers
    0.13
    ations
    0.12
    edly
    0.12
    able
    0.11
    ational
    0.10
    ated
    0.09
    ive
    0.09
    anker
    0.09
    ative
    0.09
    Activations Density 0.012%

    No Known Activations