© 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. 3672
    Prev
    Next
    INDEX
    Explanations

    ratio of

    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
    shaw
    -0.09
    ston
    -0.09
    destination
    -0.09
    zik
    -0.09
    ajar
    -0.08
    ovsky
    -0.08
    Ĺ
    -0.08
    dest
    -0.08
    EMY
    -0.08
    bon
    -0.08
    POSITIVE LOGITS
     ratios
    0.13
     ratio
    0.11
    ratio
    0.11
     Rat
    0.11
     rang
    0.10
    INGS
    0.10
     Ratio
    0.10
    Ratio
    0.09
    еÑģÑĤв
    0.09
     between
    0.09
    Activations Density 0.114%

    No Known Activations