© 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. 58317
    Prev
    Next
    INDEX
    Explanations

    want to select/use/own

    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
     choices
    -0.09
     falling
    -0.09
     Rupert
    -0.09
     rencontrer
    -0.08
     choice
    -0.08
    falls
    -0.08
    QB
    -0.08
     choosing
    -0.08
    fall
    -0.08
     #↵↵
    -0.08
    POSITIVE LOGITS
     Voyage
    0.09
     voyage
    0.09
    efd
    0.08
     icmp
    0.08
    chter
    0.08
     blasph
    0.08
    .depend
    0.08
    Continue
    0.08
     irreversible
    0.08
    arter
    0.08
    Activations Density 0.005%

    No Known Activations