© 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. 56368
    Prev
    Next
    INDEX
    Explanations

    actions that create or modify things

    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
    bilt
    -0.09
     Qué
    -0.09
    Fun
    -0.08
    wers
    -0.08
     Mundo
    -0.08
     repeatedly
    -0.08
     Fun
    -0.08
    erm
    -0.08
     Pir
    -0.08
     sourced
    -0.08
    POSITIVE LOGITS
     avail
    0.10
     comps
    0.10
     compreh
    0.08
    rex
    0.08
     av
    0.08
     accr
    0.08
     nicely
    0.08
     instrumental
    0.07
    ury
    0.07
    overe
    0.07
    Activations Density 0.094%

    No Known Activations