© 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. 2671
    Prev
    Next
    INDEX
    Explanations

    sentence beginnings

    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
     Finally
    -0.13
    Lastly
    -0.12
    Finally
    -0.12
     Lastly
    -0.12
     finally
    -0.11
    ¡°
    -0.10
    ariat
    -0.09
    inally
    -0.08
    lake
    -0.08
    amping
    -0.08
    POSITIVE LOGITS
    assic
    0.10
    erge
    0.09
    iani
    0.08
     anyways
    0.08
    ande
    0.08
    andalone
    0.08
     shl
    0.08
    è¾
    0.08
     opinion
    0.07
    aint
    0.07
    Activations Density 0.360%

    No Known Activations