© 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. 57427
    Prev
    Next
    INDEX
    Explanations

    operators and their usage

    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
     letter
    -0.07
     ethn
    -0.07
    zo
    -0.07
    engeance
    -0.07
     Intersection
    -0.07
     endeavor
    -0.06
    çľģ
    -0.06
     Medium
    -0.06
     cardinal
    -0.06
     increments
    -0.06
    POSITIVE LOGITS
    unda
    0.11
    abee
    0.10
    alfa
    0.10
    ery
    0.10
     Fi
    0.10
    isz
    0.10
    eger
    0.10
     braz
    0.10
    ãĥĥ
    0.09
     æݧ
    0.09
    Activations Density 0.027%

    No Known Activations