© 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. 57965
    Prev
    Next
    INDEX
    Explanations

    section headers or keywords

    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
    eldo
    -0.09
    aber
    -0.09
    [âĢ¦
    -0.09
     juni
    -0.08
     Alleg
    -0.08
    agas
    -0.08
     Pred
    -0.08
    INAL
    -0.08
     allegedly
    -0.08
    elts
    -0.08
    POSITIVE LOGITS
    ism
    0.09
    ison
    0.08
     sis
    0.08
    orna
    0.08
    blank
    0.08
    adin
    0.08
     vic
    0.08
     Machinery
    0.08
     Petro
    0.08
    IGH
    0.08
    Activations Density 0.007%

    No Known Activations