© 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. 56309
    Prev
    Next
    INDEX
    Explanations

    verbs like building, sold, commissioned

    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
     concerns
    -0.10
    idia
    -0.08
     starting
    -0.08
     efficiently
    -0.08
     determination
    -0.08
     co
    -0.08
     Hook
    -0.08
     Constit
    -0.08
     disagreed
    -0.08
    ber
    -0.08
    POSITIVE LOGITS
    -aligned
    0.08
    ktop
    0.08
     toy
    0.08
    rim
    0.08
    meld
    0.08
    engo
    0.08
    mund
    0.07
     nearest
    0.07
    ¢åįķ
    0.07
    istine
    0.07
    Activations Density 0.054%

    No Known Activations