© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 2527
    Prev
    Next
    INDEX
    Explanations

    mistakes and unintended consequences

    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
    ilan
    -0.10
    anel
    -0.09
     wasted
    -0.09
     Farm
    -0.09
     Cho
    -0.09
    .singleton
    -0.09
     deployments
    -0.09
    rib
    -0.08
    cker
    -0.08
    vars
    -0.08
    POSITIVE LOGITS
     accidentally
    0.21
     inadvertently
    0.17
     accidents
    0.14
     accident
    0.14
     unintention
    0.13
     mish
    0.12
     accidental
    0.12
     mistakenly
    0.11
     forgetting
    0.10
     inadvert
    0.10
    Activations Density 0.319%

    No Known Activations