© 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. 4194
    Prev
    Next
    INDEX
    Explanations

    option / choice

    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
     beg
    -0.08
     anyway
    -0.07
     fertile
    -0.07
     benefici
    -0.07
     themselves
    -0.07
     anyways
    -0.07
     Silk
    -0.07
     Robin
    -0.07
     owe
    -0.06
    isin
    -0.06
    POSITIVE LOGITS
     preferable
    0.14
    /pub
    0.11
    ovie
    0.10
     suffice
    0.10
     preferred
    0.10
    EDGE
    0.10
    sov
    0.10
    ices
    0.10
     desirable
    0.10
    lm
    0.09
    Activations Density 0.342%

    No Known Activations