© 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. 3750
    Prev
    Next
    INDEX
    Explanations

    that/those, followed by nouns

    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
     Barn
    -0.09
     reasoning
    -0.09
    former
    -0.08
     above
    -0.08
     kind
    -0.08
    Ú©
    -0.07
     type
    -0.07
     selective
    -0.07
     phenomenon
    -0.07
     triple
    -0.07
    POSITIVE LOGITS
    entiful
    0.10
    uld
    0.10
    dda
    0.10
     dah
    0.10
    gf
    0.09
    beer
    0.09
    lyn
    0.09
    elor
    0.09
    rys
    0.09
     unb
    0.09
    Activations Density 0.231%

    No Known Activations