© 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. 57353
    Prev
    Next
    INDEX
    Explanations

    hidden, concealed, or unseen

    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
     dav
    -0.10
     Incorporated
    -0.10
     boob
    -0.10
     Corps
    -0.09
     purge
    -0.09
     Rav
    -0.09
     (...)
    -0.09
    orate
    -0.09
     conj
    -0.09
     pur
    -0.09
    POSITIVE LOGITS
     hidden
    0.20
     disguised
    0.17
     concealed
    0.17
     Hidden
    0.16
     invisible
    0.16
     invis
    0.16
     unseen
    0.14
     albeit
    0.13
    hidden
    0.13
     disguise
    0.13
    Activations Density 0.086%

    No Known Activations