© 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. 190
    Prev
    Next
    INDEX
    Explanations

    mathematical variable assignments

    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
    ity
    -0.10
    fef
    -0.09
    nze
    -0.09
    ames
    -0.09
    INET
    -0.09
    faf
    -0.09
    asting
    -0.09
    ']*
    -0.09
    æŃ
    -0.08
    oire
    -0.08
    POSITIVE LOGITS
     lh
    0.09
     dab
    0.08
     breakthrough
    0.08
     lint
    0.07
     demonstr
    0.07
     Concert
    0.07
    .ones
    0.07
    kon
    0.07
     charcoal
    0.07
     Pel
    0.07
    Activations Density 0.437%

    No Known Activations