© 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. 57987
    Prev
    Next
    INDEX
    Explanations

    or, other, pair

    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
     '..',
    -0.10
    sher
    -0.10
    bil
    -0.09
    @js
    -0.09
    otron
    -0.09
    uez
    -0.09
     accidental
    -0.09
     Await
    -0.08
     permalink
    -0.08
    wart
    -0.08
    POSITIVE LOGITS
     Kr
    0.08
     singles
    0.08
    queen
    0.08
     Sav
    0.07
    orz
    0.07
     Exc
    0.07
     Trojan
    0.07
    ás
    0.07
    Kr
    0.07
     Quinn
    0.07
    Activations Density 0.101%

    No Known Activations