© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 56841
    Prev
    Next
    INDEX
    Explanations

    megachurches, megawatt, megavoltage, megasthenes, megadeth, megastar

    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
     Venture
    -0.11
    rig
    -0.11
    ï¸
    -0.11
    utes
    -0.10
    ippy
    -0.10
     Provid
    -0.10
    .nano
    -0.10
    ports
    -0.10
    PING
    -0.10
     Pane
    -0.10
    POSITIVE LOGITS
    atic
    0.07
     trait
    0.07
    al
    0.06
    ève
    0.06
     Ort
    0.06
     sign
    0.06
     cork
    0.06
     Wal
    0.06
     anew
    0.06
    aday
    0.06
    Activations Density 0.005%

    No Known Activations