© 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. 1133
    Prev
    Next
    INDEX
    Explanations

    technical operations and organization

    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
    ambda
    -0.11
    /devices
    -0.10
     Pen
    -0.10
    /android
    -0.09
    -ser
    -0.09
    Serializable
    -0.09
     Iranians
    -0.09
    .Alpha
    -0.09
    -Jul
    -0.09
     ={↵
    -0.09
    POSITIVE LOGITS
     them
    0.15
     the
    0.13
     your
    0.13
     their
    0.12
     everything
    0.12
     existing
    0.11
     siÄĻ
    0.10
    /opt
    0.10
     certain
    0.10
     each
    0.10
    Activations Density 2.373%

    No Known Activations