© 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. 8899
    Prev
    Next
    INDEX
    Explanations

    removing something

    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
    rew
    -0.11
    om
    -0.10
    pone
    -0.09
     PX
    -0.09
    oner
    -0.09
    erview
    -0.09
    anth
    -0.09
     elimination
    -0.09
    obel
    -0.08
    alt
    -0.08
    POSITIVE LOGITS
    ÑģÑı
    0.10
     obstacles
    0.10
    ulen
    0.10
     Crest
    0.09
     burden
    0.09
    inton
    0.09
     Tavern
    0.09
    ĻĤ
    0.08
     obstacle
    0.08
    icks
    0.08
    Activations Density 0.088%

    No Known Activations