© 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. 53959
    Prev
    Next
    INDEX
    Explanations

    reports released or published

    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
    اد
    -0.08
     Shadows
    -0.07
    ä¸
    -0.07
    اب
    -0.07
     stained
    -0.07
    kit
    -0.07
     vain
    -0.07
    oo
    -0.07
     Alone
    -0.07
     whatever
    -0.07
    POSITIVE LOGITS
    iego
    0.10
    OLF
    0.10
    _restore
    0.09
    iene
    0.09
    addle
    0.09
    attend
    0.09
     quarter
    0.09
     retrie
    0.09
     Goat
    0.09
     ghost
    0.09
    Activations Density 0.094%

    No Known Activations