© 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. 55023
    Prev
    Next
    INDEX
    Explanations

    percentages or numbers

    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
    ward
    -0.07
    sein
    -0.05
     inet
    -0.05
    vault
    -0.05
     rec
    -0.05
    avor
    -0.05
    b
    -0.05
     Recover
    -0.05
    der
    -0.05
    icts
    -0.05
    POSITIVE LOGITS
    –↵↵
    0.12
    [js
    0.11
    allis
    0.11
    ellipsis
    0.11
    eden
    0.11
    ADS
    0.11
    еÑģÑģ
    0.11
    .sk
    0.11
    ý
    0.11
    igans
    0.11
    Activations Density 0.002%

    No Known Activations