© 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. 61725
    Prev
    Next
    INDEX
    Explanations

    bone, prostate, cognitive, CV function

    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
    opol
    -0.10
     paralyzed
    -0.09
     Cumberland
    -0.08
    icide
    -0.08
     wrest
    -0.08
     indu
    -0.08
    Lab
    -0.08
     Liber
    -0.08
    move
    -0.08
     lang
    -0.07
    POSITIVE LOGITS
    .ensure
    0.10
     sketch
    0.09
    wise
    0.09
     wisdom
    0.08
     spice
    0.08
    uid
    0.08
     functionality
    0.08
    RAP
    0.08
     Cl
    0.08
    maj
    0.08
    Activations Density 0.151%

    No Known Activations