© 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. 99
    Prev
    Next
    INDEX
    Explanations

    as a, as well, as shown

    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
     as
    -0.11
    以
    -0.10
    hir
    -0.07
    acter
    -0.07
    pus
    -0.07
     assembling
    -0.07
    avier
    -0.07
    nex
    -0.07
    vro
    -0.07
    空
    -0.07
    POSITIVE LOGITS
     opposed
    0.27
     follows
    0.23
    cert
    0.22
    cribed
    0.21
     well
    0.21
     regards
    0.21
    sembl
    0.20
     soon
    0.20
     oppose
    0.20
    cribing
    0.20
    Activations Density 0.680%

    No Known Activations