© 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. 1467
    Prev
    Next
    INDEX
    Explanations

    Copyright (C)

    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
    RNA
    -0.14
    DNA
    -0.12
    .k
    -0.11
    TION
    -0.11
    E
    -0.11
    Evt
    -0.10
    rastructure
    -0.10
    EFR
    -0.10
    bsites
    -0.09
    EZ
    -0.09
    POSITIVE LOGITS
    c
    0.18
    t
    0.16
    b
    0.14
    aaS
    0.13
    s
    0.13
    /OR
    0.13
    m
    0.13
    p
    0.13
    y
    0.13
    a
    0.13
    Activations Density 4.314%

    No Known Activations