© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 8721
    Prev
    Next
    INDEX
    Explanations

    when [action verb]

    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
    Negative Logits
     misunderstanding
    -0.09
    amu
    -0.09
     everywhere
    -0.08
    atcher
    -0.08
     Bloom
    -0.08
    ival
    -0.08
     once
    -0.08
    _self
    -0.08
     Nich
    -0.08
    bab
    -0.08
    POSITIVE LOGITS
     designing
    0.10
    ë¸
    0.09
     design
    0.09
    eln
    0.08
     comeback
    0.08
    FromFile
    0.08
    parseFloat
    0.08
    undra
    0.08
     unavoid
    0.08
    IDL
    0.08
    Activations Density 0.419%

    No Known Activations