© 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. 56409
    Prev
    Next
    INDEX
    Explanations

    citation marker

    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
    TypeEnum
    -0.11
     third
    -0.10
    ilde
    -0.10
     BOTH
    -0.10
    dda
    -0.09
    ibs
    -0.09
     narc
    -0.09
    cea
    -0.09
    /chart
    -0.09
    stro
    -0.09
    POSITIVE LOGITS
    aris
    0.09
     Crypt
    0.08
     Rad
    0.08
    __(
    0.08
     leaf
    0.08
     corner
    0.08
    Rad
    0.08
     accident
    0.08
     erg
    0.08
     Cunningham
    0.08
    Activations Density 0.004%

    No Known Activations