© 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. 504
    Prev
    Next
    INDEX
    Explanations

    relative file paths

    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
     Bard
    -0.11
     Bare
    -0.11
    "-
    -0.10
     naj
    -0.10
    overe
    -0.10
    alion
    -0.10
    aket
    -0.10
     Sovere
    -0.10
     No
    -0.10
     Few
    -0.09
    POSITIVE LOGITS
     misc
    0.10
    misc
    0.08
    /*/
    0.08
     core
    0.08
     impe
    0.08
     dela
    0.07
    imas
    0.07
    ITA
    0.07
    ForRow
    0.07
     research
    0.06
    Activations Density 1.787%

    No Known Activations