© 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. 3902
    Prev
    Next
    INDEX
    Explanations

    and a

    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
    ány
    -0.09
    acre
    -0.09
    igin
    -0.09
    nip
    -0.09
    aus
    -0.09
    ilon
    -0.08
    éc
    -0.08
     Quantity
    -0.08
    ást
    -0.08
     wes
    -0.08
    POSITIVE LOGITS
     plenty
    0.19
     lots
    0.15
     ample
    0.13
     Plenty
    0.13
     a
    0.12
     Lots
    0.11
    lots
    0.11
     an
    0.11
     fewer
    0.10
     enough
    0.10
    Activations Density 0.427%

    No Known Activations