© 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. 58313
    Prev
    Next
    INDEX
    Explanations

    ending punctuation, lists, or conjunctions

    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
     unintention
    -0.08
     null
    -0.08
    ems
    -0.08
    tti
    -0.08
     Hog
    -0.07
    MM
    -0.07
    iggs
    -0.07
     duty
    -0.07
     magg
    -0.07
     Rain
    -0.07
    POSITIVE LOGITS
     finally
    0.11
    icos
    0.10
    ico
    0.10
    tracts
    0.10
    ayah
    0.10
     */↵↵↵↵
    0.10
    ros
    0.09
    .hy
    0.09
     Ult
    0.09
     prep
    0.09
    Activations Density 0.089%

    No Known Activations