© 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. 3633
    Prev
    Next
    INDEX
    Explanations

    defined as threshold

    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
    kek
    -0.08
    ена
    -0.08
    amus
    -0.08
    cest
    -0.08
    olin
    -0.07
    oko
    -0.07
    PEND
    -0.07
     Mayer
    -0.07
    нов
    -0.07
    Äĥng
    -0.07
    POSITIVE LOGITS
     threshold
    0.39
     thresholds
    0.37
     Threshold
    0.36
    Threshold
    0.32
     cutoff
    0.30
    threshold
    0.29
    _threshold
    0.28
    .threshold
    0.24
     thresh
    0.24
    reshold
    0.21
    Activations Density 0.484%

    No Known Activations