© 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. 56935
    Prev
    Next
    INDEX
    Explanations

    already existing

    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
     finally
    -0.10
     final
    -0.09
    .fin
    -0.09
     painstaking
    -0.08
     finalized
    -0.08
     Final
    -0.08
     ultimately
    -0.08
     FINAL
    -0.08
    Final
    -0.08
    Fin
    -0.08
    POSITIVE LOGITS
     already
    0.30
     Already
    0.29
    Already
    0.27
     immediately
    0.26
    already
    0.23
     immediate
    0.22
     Immediately
    0.21
     instantly
    0.20
    Immediately
    0.20
     Immediate
    0.19
    Activations Density 0.094%

    No Known Activations