© 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. 1180
    Prev
    Next
    INDEX
    Explanations

    suffixes like -s, -d, -f, -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
    lobal
    -0.11
    ession
    -0.11
    wer
    -0.10
    ource
    -0.10
    asant
    -0.09
    eshire
    -0.09
    ych
    -0.09
    sys
    -0.09
    ablish
    -0.08
    edy
    -0.08
    POSITIVE LOGITS
    i
    0.24
    an
    0.18
    u
    0.18
    al
    0.17
    a
    0.16
    y
    0.16
    at
    0.16
    el
    0.14
    iard
    0.14
    on
    0.14
    Activations Density 0.974%

    No Known Activations