© 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. 62005
    Prev
    Next
    INDEX
    Explanations

    not or lack of

    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
    iral
    -0.08
    ft
    -0.08
    iron
    -0.08
    cstdint
    -0.08
    irl
    -0.08
     aest
    -0.08
    awan
    -0.08
    igen
    -0.08
     Vict
    -0.07
     internally
    -0.07
    POSITIVE LOGITS
    charm
    0.10
    jom
    0.09
    eus
    0.09
     Herb
    0.09
     Crossing
    0.09
     sequential
    0.09
    ilos
    0.09
    spinner
    0.09
    ORM
    0.09
    egis
    0.08
    Activations Density 0.053%

    No Known Activations