© 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. 58628
    Prev
    Next
    INDEX
    Explanations

    following the passage

    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
    udas
    -0.08
    Vs
    -0.08
     looming
    -0.08
    -li
    -0.08
    .u
    -0.07
     suff
    -0.07
    bre
    -0.07
    eti
    -0.07
    enschaft
    -0.07
     tripod
    -0.07
    POSITIVE LOGITS
     footsteps
    0.13
     pied
    0.11
     trail
    0.11
     trends
    0.11
     logic
    0.10
     closely
    0.10
    aggi
    0.09
     lead
    0.09
     leads
    0.09
     tradition
    0.09
    Activations Density 0.042%

    No Known Activations