© 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. 55823
    Prev
    Next
    INDEX
    Explanations

    arithmetic sequence prediction

    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
    wards
    -0.09
    sid
    -0.09
    phia
    -0.09
     Lov
    -0.09
     Sid
    -0.08
     forwards
    -0.08
    aal
    -0.08
     Plat
    -0.08
    etheless
    -0.08
     hyper
    -0.08
    POSITIVE LOGITS
    ickers
    0.09
     Mercer
    0.08
    rek
    0.08
     Flu
    0.08
    izzo
    0.08
    cker
    0.08
    anel
    0.08
    AMI
    0.08
    ems
    0.08
    umper
    0.08
    Activations Density 0.020%

    No Known Activations