© 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. 61361
    Prev
    Next
    INDEX
    Explanations

    broken or damaged things

    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
    ums
    -0.08
     unavoidable
    -0.08
    unger
    -0.08
     ìł
    -0.08
    pron
    -0.07
    sten
    -0.07
     boyc
    -0.07
     disagreement
    -0.07
    occo
    -0.07
    Stuff
    -0.07
    POSITIVE LOGITS
    zo
    0.10
    nees
    0.10
     vill
    0.09
    han
    0.09
    ernen
    0.09
    sey
    0.09
     millennium
    0.09
     Promise
    0.09
    ainen
    0.08
    erring
    0.08
    Activations Density 0.061%

    No Known Activations