© 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. 57304
    Prev
    Next
    INDEX
    Explanations

    cost of

    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
     costing
    -0.13
     á
    -0.12
     expenditure
    -0.12
    è´¹
    -0.12
     cheaper
    -0.11
     expensive
    -0.11
     costly
    -0.10
     spending
    -0.10
     costs
    -0.10
    èĬ
    -0.10
    POSITIVE LOGITS
     Operation
    0.08
     alterations
    0.08
     prec
    0.07
     altered
    0.07
    kl
    0.07
    att
    0.07
     alternatives
    0.07
    963
    0.07
     Prem
    0.07
     att
    0.07
    Activations Density 0.031%

    No Known Activations