© 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. 4514
    Prev
    Next
    INDEX
    Explanations

    code closing delimiters

    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
    @Table
    -0.09
    emp
    -0.09
    Ce
    -0.09
    AK
    -0.08
     acknowled
    -0.08
     Sar
    -0.08
    ture
    -0.08
    .Pe
    -0.08
    su
    -0.08
    Edward
    -0.08
    POSITIVE LOGITS
     (("
    0.08
    âĢ°
    0.08
    avel
    0.08
     Zodiac
    0.08
    locks
    0.08
    .pm
    0.08
     Morrison
    0.07
    -pad
    0.07
     Brent
    0.07
    iese
    0.07
    Activations Density 0.307%

    No Known Activations