© 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. 2035
    Prev
    Next
    INDEX
    Explanations

    'and' followed by verb or conjunction

    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
     whom
    -0.11
     ensued
    -0.11
     alike
    -0.10
     bothering
    -0.10
     relent
    -0.09
     himself
    -0.09
    ially
    -0.09
    nt
    -0.09
    oldem
    -0.08
     arisen
    -0.08
    POSITIVE LOGITS
     can
    0.17
     cannot
    0.15
     may
    0.15
     could
    0.14
    /or
    0.13
     there
    0.13
     will
    0.12
     thus
    0.12
     it
    0.12
     must
    0.12
    Activations Density 1.295%

    No Known Activations