© 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. 3669
    Prev
    Next
    INDEX
    Explanations

    bridge makes cheaper

    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
    inha
    -0.12
     (?)
    -0.11
     (?
    -0.11
    blind
    -0.10
     Bits
    -0.10
     sections
    -0.09
     physics
    -0.09
     officially
    -0.09
    illions
    -0.09
    eti
    -0.09
    POSITIVE LOGITS
     synerg
    0.10
     surviv
    0.09
     early
    0.08
     fian
    0.08
     situ
    0.08
     utility
    0.08
    sh
    0.08
     Early
    0.08
     paradigm
    0.08
     synergy
    0.08
    Activations Density 0.086%

    No Known Activations