© 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. 4568
    Prev
    Next
    INDEX
    Explanations

    subject to

    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
    iec
    -0.10
     Replay
    -0.10
    endregion
    -0.10
     rake
    -0.10
    awk
    -0.09
     arcs
    -0.09
     arc
    -0.09
    /json
    -0.09
     Outside
    -0.09
    _Rem
    -0.09
    POSITIVE LOGITS
    acer
    0.07
     threat
    0.07
     threats
    0.07
    atus
    0.07
     parallel
    0.07
     Mata
    0.06
     mess
    0.06
    ôt
    0.06
     ign
    0.06
    enty
    0.06
    Activations Density 0.460%

    No Known Activations