© 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. 61345
    Prev
    Next
    INDEX
    Explanations

    physical objects and their states

    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
     Pat
    -0.09
     fuzz
    -0.09
     directions
    -0.09
     Care
    -0.08
    Care
    -0.08
    Continue
    -0.08
    å±
    -0.08
     conducive
    -0.08
     pat
    -0.08
    Posts
    -0.08
    POSITIVE LOGITS
    arius
    0.10
    apon
    0.09
     (;;)
    0.09
    /display
    0.08
    bei
    0.08
     immersed
    0.08
     Threshold
    0.08
    ëħ
    0.08
     Gra
    0.08
    hurst
    0.08
    Activations Density 0.071%

    No Known Activations