© 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. 2742
    Prev
    Next
    INDEX
    Explanations

    to begin, to witness, to play

    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
     arriving
    -0.13
     arrive
    -0.10
     sap
    -0.09
    .Scan
    -0.09
     arrives
    -0.09
     convin
    -0.09
     arrived
    -0.08
    antic
    -0.08
     lo
    -0.08
     conveying
    -0.08
    POSITIVE LOGITS
     inspect
    0.11
    lh
    0.10
     inspection
    0.09
     closer
    0.09
    etu
    0.09
     undergo
    0.08
     wreak
    0.08
    datable
    0.08
     Edition
    0.08
     Inspection
    0.08
    Activations Density 0.227%

    No Known Activations