© 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. 3908
    Prev
    Next
    INDEX
    Explanations

    Indian names and titles

    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
    iscard
    -0.12
     coz
    -0.10
     sto
    -0.10
    aget
    -0.10
    Ef
    -0.10
     Majority
    -0.10
     Filip
    -0.10
    Hover
    -0.10
     Hag
    -0.09
    ozo
    -0.09
    POSITIVE LOGITS
     Sonia
    0.09
    etty
    0.09
    rip
    0.09
     rip
    0.09
     MLA
    0.08
    amma
    0.08
    àµį
    0.08
     aur
    0.08
    rale
    0.08
     Wings
    0.08
    Activations Density 0.734%

    No Known Activations