© 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. 56635
    Prev
    Next
    INDEX
    Explanations

    trace down or isolate issues

    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
     drowning
    -0.08
     environments
    -0.07
     paced
    -0.07
     cumpl
    -0.07
     triple
    -0.07
     environment
    -0.07
     Burn
    -0.07
     hoax
    -0.07
     qualifying
    -0.07
     Triple
    -0.07
    POSITIVE LOGITS
     traced
    0.12
     origins
    0.11
     roots
    0.11
     trace
    0.11
     tracing
    0.11
     traces
    0.10
     backwards
    0.10
    _down
    0.10
    -down
    0.10
     hon
    0.10
    Activations Density 0.118%

    No Known Activations