© 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. 780
    Prev
    Next
    INDEX
    Explanations

    counting or referring to one

    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
    udas
    -0.10
    ONES
    -0.09
    inus
    -0.09
    ingers
    -0.09
    /MIT
    -0.09
    iers
    -0.09
    /Add
    -0.09
    findAll
    -0.09
    wang
    -0.09
     :=↵
    -0.08
    POSITIVE LOGITS
     per
    0.15
    /single
    0.14
    (s
    0.13
    atat
    0.13
    (single
    0.12
     each
    0.12
     suffice
    0.11
    -two
    0.10
    —one
    0.10
    -single
    0.10
    Activations Density 1.391%

    No Known Activations