© 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. 2089
    Prev
    Next
    INDEX
    Explanations

    since then

    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
     recently
    -0.13
    elper
    -0.10
    recent
    -0.10
     hoy
    -0.09
    ERA
    -0.09
    elon
    -0.09
    hind
    -0.08
     menace
    -0.08
     indent
    -0.08
    resar
    -0.08
    POSITIVE LOGITS
     has
    0.12
     Ive
    0.12
     ive
    0.12
     hasn
    0.11
    ’ve
    0.11
     have
    0.10
    ve
    0.10
    've
    0.10
     been
    0.10
     haven
    0.10
    Activations Density 0.221%

    No Known Activations