© 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. 1009
    Prev
    Next
    INDEX
    Explanations

    sup following words

    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
    aker
    -0.10
    æĪ·
    -0.09
    anager
    -0.09
    reed
    -0.09
    <<<
    -0.09
    nect
    -0.09
    tron
    -0.09
    &r
    -0.09
    Ñħ
    -0.09
     har
    -0.09
    POSITIVE LOGITS
    ior
    0.12
    ().__
    0.10
    ì¹ĺ
    0.10
    ordinate
    0.10
    plementary
    0.09
    isory
    0.09
    ément
    0.08
    posed
    0.08
    kat
    0.08
     quiet
    0.08
    Activations Density 0.579%

    No Known Activations