© 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. 3616
    Prev
    Next
    INDEX
    Explanations

    treeview, digital TV, certified, parameter

    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
    ire
    -0.08
     Además
    -0.08
    eln
    -0.08
    lick
    -0.08
     formally
    -0.07
     Hers
    -0.07
     prevailing
    -0.07
    -centered
    -0.07
     обÑĬ
    -0.07
    lect
    -0.07
    POSITIVE LOGITS
    .cur
    0.10
    deo
    0.10
     youngest
    0.09
     worst
    0.09
    macen
    0.09
    fec
    0.09
     Conserv
    0.09
    为空
    0.09
     inactive
    0.09
     |-
    0.09
    Activations Density 0.545%

    No Known Activations