© 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. 3213
    Prev
    Next
    INDEX
    Explanations

    compatibility or response to questions

    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
    tep
    -0.11
     preparations
    -0.09
    quil
    -0.08
     estimation
    -0.08
    ople
    -0.08
     Springs
    -0.08
     determination
    -0.07
     ÑģоÑģÑĤ
    -0.07
     networks
    -0.07
     Conditions
    -0.07
    POSITIVE LOGITS
     decisions
    0.14
     occasionally
    0.14
     occasional
    0.13
     commands
    0.13
     actions
    0.12
     Occasionally
    0.12
     Whenever
    0.12
     whenever
    0.12
    getattr
    0.12
    Whenever
    0.12
    Activations Density 0.539%

    No Known Activations