© 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. 54553
    Prev
    Next
    INDEX
    Explanations

    locations, records, calls, details, queries

    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
    ouv
    -0.08
    avier
    -0.08
    rror
    -0.08
    vale
    -0.08
    acher
    -0.07
    Hor
    -0.07
     Flyers
    -0.07
     Horizon
    -0.07
    elig
    -0.07
    Calcul
    -0.07
    POSITIVE LOGITS
     movement
    0.12
     movements
    0.11
     tong
    0.10
     every
    0.10
     Movement
    0.10
     records
    0.10
     slightest
    0.10
    strup
    0.09
     pattern
    0.09
     Records
    0.09
    Activations Density 0.081%

    No Known Activations