© 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. 139
    Prev
    Next
    INDEX
    Explanations

    perhaps, possibly, or maybe

    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
     reportedly
    -0.20
     usually
    -0.15
     often
    -0.14
     apparently
    -0.14
     typically
    -0.13
    usually
    -0.13
     allegedly
    -0.13
     seemingly
    -0.13
     essentially
    -0.12
     ostensibly
    -0.12
    POSITIVE LOGITS
     somehow
    0.25
     somewhere
    0.22
     or
    0.18
     somew
    0.16
     something
    0.16
     someday
    0.13
    something
    0.13
     possibly
    0.12
     или
    0.12
     SOME
    0.12
    Activations Density 2.866%

    No Known Activations