© 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. 57611
    Prev
    Next
    INDEX
    Explanations

    knew what happened

    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
    urn
    -0.07
     corrobor
    -0.07
     tol
    -0.07
     ethn
    -0.07
     validity
    -0.06
    Images
    -0.06
     betr
    -0.06
    reed
    -0.06
    нÑı
    -0.06
     myself
    -0.06
    POSITIVE LOGITS
    ppe
    0.12
    itch
    0.11
     Initially
    0.11
     evolving
    0.11
    amina
    0.10
    [Index
    0.10
    éis
    0.10
    protocols
    0.10
    scalar
    0.10
    enis
    0.10
    Activations Density 0.105%

    No Known Activations