© 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. 556
    Prev
    Next
    INDEX
    Explanations

    names ending in on/amon

    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
    ë¡ľ
    -0.14
    lear
    -0.11
    enton
    -0.11
    leton
    -0.10
    tte
    -0.10
    opper
    -0.10
    les
    -0.09
    ло
    -0.09
    eing
    -0.09
    enson
    -0.09
    POSITIVE LOGITS
    ned
    0.17
    ics
    0.17
    nie
    0.17
    uevo
    0.16
    ning
    0.15
    nette
    0.15
    ny
    0.15
    nement
    0.14
    ni
    0.14
    nen
    0.13
    Activations Density 1.528%

    No Known Activations