© 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. 1580
    Prev
    Next
    INDEX
    Explanations

    concluding words and phrases

    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
     and
    -0.13
     firstly
    -0.12
     however
    -0.10
    -0.09
    :
    -0.09
     Tamb
    -0.08
    NullException
    -0.08
     kidding
    -0.08
     originally
    -0.07
    teen
    -0.07
    POSITIVE LOGITS
     accordingly
    0.30
     consequently
    0.27
     therefore
    0.26
     thereafter
    0.20
     consequ
    0.20
     thereby
    0.20
     subsequently
    0.18
     thus
    0.17
     subsequent
    0.16
    Therefore
    0.16
    Activations Density 2.592%

    No Known Activations