© 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. 58105
    Prev
    Next
    INDEX
    Explanations

    configuration settings

    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
    Temporary
    -0.09
     microscopic
    -0.09
    åħ±
    -0.08
     temporarily
    -0.08
     temporary
    -0.08
     Flexible
    -0.08
     Lesb
    -0.08
    ToLocal
    -0.08
    Flexible
    -0.08
    aff
    -0.08
    POSITIVE LOGITS
     adult
    0.11
     optimizations
    0.11
    ledge
    0.10
     streamlined
    0.10
     optimization
    0.10
     optimized
    0.10
     finalized
    0.10
    itemap
    0.10
     Optimization
    0.09
     devoid
    0.09
    Activations Density 0.008%

    No Known Activations