© 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. 55500
    Prev
    Next
    INDEX
    Explanations

    units of measurement (Hz, V, ms, rpm)

    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
     cred
    -0.08
    imas
    -0.08
     Bened
    -0.08
     cro
    -0.08
    EDI
    -0.07
     suffers
    -0.07
    SM
    -0.07
    izza
    -0.07
     anno
    -0.07
    -design
    -0.07
    POSITIVE LOGITS
     settings
    0.12
     setting
    0.11
    mode
    0.11
     Settings
    0.10
    .xml
    0.10
     preset
    0.10
     mode
    0.09
     medium
    0.09
    auto
    0.09
    _medium
    0.09
    Activations Density 0.047%

    No Known Activations