© 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. 472
    Prev
    Next
    INDEX
    Explanations

    past tense findings or results

    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
     ultimately
    -0.12
     purported
    -0.11
     ostensibly
    -0.11
     oddly
    -0.11
     decidedly
    -0.11
     foundational
    -0.11
    —and
    -0.11
     circa
    -0.10
     foc
    -0.10
     potentially
    -0.10
    POSITIVE LOGITS
     equipments
    0.22
     firstly
    0.20
     nowadays
    0.17
     Nowadays
    0.16
     informations
    0.15
     meanwhile
    0.14
     recommand
    0.14
     advoc
    0.14
    ï¼į
    0.14
     splitted
    0.13
    Activations Density 6.004%

    No Known Activations