© 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. 1682
    Prev
    Next
    INDEX
    Explanations

    numbers in diagrams

    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
     Preview
    -0.08
    =User
    -0.06
     Roc
    -0.06
    ou
    -0.06
    rtl
    -0.06
    iku
    -0.06
    ist
    -0.06
    sts
    -0.06
     ÈĻi
    -0.05
    ism
    -0.05
    POSITIVE LOGITS
    /OR
    0.13
    /of
    0.11
    criptor
    0.11
     arrows
    0.10
     OTHERWISE
    0.10
    .compress
    0.10
    .GO
    0.10
     {...
    0.10
    Rh
    0.10
    -arrow
    0.10
    Activations Density 0.290%

    No Known Activations