© 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. 3667
    Prev
    Next
    INDEX
    Explanations

    rare and uncommon

    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
    YO
    -0.09
     Armour
    -0.09
     tumble
    -0.09
    项
    -0.08
     positional
    -0.08
    Cele
    -0.08
    isco
    -0.08
     Sizes
    -0.08
    nos
    -0.08
     Voy
    -0.08
    POSITIVE LOGITS
     rare
    0.36
     Rare
    0.29
     rarity
    0.27
    Rare
    0.24
     uncommon
    0.21
     rarely
    0.20
     rar
    0.19
     seldom
    0.16
     unusually
    0.14
     unusual
    0.13
    Activations Density 0.290%

    No Known Activations