© 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. 54977
    Prev
    Next
    INDEX
    Explanations

    INC, organizations, institutions

    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
    achat
    -0.10
    airo
    -0.10
    eki
    -0.10
    imit
    -0.09
    spin
    -0.09
     chocol
    -0.09
    chang
    -0.09
     meg
    -0.08
     impression
    -0.08
    \data
    -0.08
    POSITIVE LOGITS
    -loving
    0.10
    /people
    0.09
     duo
    0.09
     orchestrated
    0.09
     Institution
    0.08
    erta
    0.08
     squeeze
    0.08
    xe
    0.08
    ca
    0.08
    /person
    0.08
    Activations Density 0.238%

    No Known Activations