© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 1563
    Prev
    Next
    INDEX
    Explanations

    ports, rail, transfer, host, importance, types

    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
    aina
    -0.10
    éĵ
    -0.08
    ffc
    -0.08
    immel
    -0.08
    aka
    -0.08
    bak
    -0.08
     ($(
    -0.08
    owl
    -0.08
    MMC
    -0.08
    Perm
    -0.08
    POSITIVE LOGITS
     tersebut
    0.18
     nÃły
    0.13
    ses
    0.12
     latter
    0.10
    ment
    0.09
     these
    0.09
    .setter
    0.08
     Dit
    0.08
    è¿Ļ
    0.08
     Tits
    0.08
    Activations Density 3.748%

    No Known Activations