© 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. 3776
    Prev
    Next
    INDEX
    Explanations

    not / anything

    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
     limitations
    -0.09
     wiping
    -0.08
     boundaries
    -0.08
    hes
    -0.08
    -Control
    -0.08
     freely
    -0.08
     stiff
    -0.08
     disbelief
    -0.08
     forgetting
    -0.08
     hes
    -0.08
    POSITIVE LOGITS
    agus
    0.11
     any
    0.11
    (any
    0.10
    cul
    0.10
     meaningful
    0.10
     anything
    0.09
     aff
    0.09
    ANY
    0.09
     interest
    0.09
     ever
    0.09
    Activations Density 0.362%

    No Known Activations