© 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. 4075
    Prev
    Next
    INDEX
    Explanations

    filtering data and actions

    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
    ente
    -0.09
    ffa
    -0.08
    fulness
    -0.08
    gor
    -0.08
    dy
    -0.08
    alla
    -0.08
     mÃŃ
    -0.08
     Dew
    -0.08
     plaisir
    -0.08
    ly
    -0.08
    POSITIVE LOGITS
     out
    0.11
    -out
    0.10
    epam
    0.10
    _SANITIZE
    0.10
    ation
    0.10
    ted
    0.09
    ered
    0.09
    amac
    0.09
    _VALIDATE
    0.09
    warnings
    0.09
    Activations Density 0.053%

    No Known Activations