© 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. 3870
    Prev
    Next
    INDEX
    Explanations

    firstly, first, initially

    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
     ALSO
    -0.11
     likewise
    -0.11
     additionally
    -0.10
     also
    -0.10
     juga
    -0.10
     nevertheless
    -0.10
    Also
    -0.10
    also
    -0.10
     Also
    -0.09
    esan
    -0.09
    POSITIVE LOGITS
     Firstly
    0.11
     firstly
    0.11
    é¦ĸ
    0.10
     first
    0.09
     enim
    0.09
     initially
    0.08
    First
    0.08
    oad
    0.08
    Indeed
    0.08
    rig
    0.07
    Activations Density 0.890%

    No Known Activations