© 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. 3317
    Prev
    Next
    INDEX
    Explanations

    vocatives and names

    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
    erves
    -0.09
    esses
    -0.09
    isse
    -0.09
    cession
    -0.08
    uci
    -0.08
     defiant
    -0.08
     GRA
    -0.08
     grading
    -0.08
    nik
    -0.08
     Civil
    -0.08
    POSITIVE LOGITS
     dear
    0.12
     mate
    0.10
     sir
    0.10
     gentlemen
    0.09
     folks
    0.09
     darling
    0.09
    Dear
    0.09
    riend
    0.09
     fellow
    0.09
    emplate
    0.08
    Activations Density 0.163%

    No Known Activations