© 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. 4830
    Prev
    Next
    INDEX
    Explanations

    special characters and separators

    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
    eld
    -0.10
     exploration
    -0.09
    (<
    -0.08
    onda
    -0.08
    egas
    -0.08
    edo
    -0.08
    ledo
    -0.08
     inse
    -0.08
     Stevenson
    -0.08
     amnesty
    -0.08
    POSITIVE LOGITS
     membr
    0.09
     Thumb
    0.09
    ramid
    0.08
    aura
    0.08
     Zur
    0.08
     Singer
    0.08
     fore
    0.08
    atron
    0.08
     trace
    0.08
     proc
    0.08
    Activations Density 0.233%

    No Known Activations