© 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. 54837
    Prev
    Next
    INDEX
    Explanations

    loop counters like i

    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
     Jes
    -0.10
    -speaking
    -0.10
     Jou
    -0.10
     Markt
    -0.09
     bounty
    -0.09
    sha
    -0.09
     Valor
    -0.09
     sil
    -0.09
    efore
    -0.09
     "";č↵č↵
    -0.09
    POSITIVE LOGITS
    anel
    0.10
    olk
    0.09
    rim
    0.08
     li
    0.08
     nic
    0.08
     genuinely
    0.07
    oub
    0.07
     scoff
    0.07
    eder
    0.07
    ker
    0.07
    Activations Density 0.009%

    No Known Activations