© 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. 2243
    Prev
    Next
    INDEX
    Explanations

    results, chapters, closure

    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
     Desde
    -0.08
    orda
    -0.08
     Hal
    -0.08
    geries
    -0.08
    bable
    -0.08
    stem
    -0.07
     dbg
    -0.07
     adhesive
    -0.07
    uru
    -0.07
    .clean
    -0.07
    POSITIVE LOGITS
     sizeof
    0.10
    rc
    0.10
     featuring
    0.10
    Meet
    0.10
     occupied
    0.10
     bout
    0.09
    ids
    0.09
     owning
    0.09
     posi
    0.09
    (typeof
    0.09
    Activations Density 0.527%

    No Known Activations