© 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. 61758
    Prev
    Next
    INDEX
    Explanations

    initials or affiliations

    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
     eds
    -0.09
     support
    -0.08
    abe
    -0.07
     dig
    -0.06
     ret
    -0.06
     naughty
    -0.06
     ran
    -0.06
     run
    -0.06
    iffe
    -0.06
     Support
    -0.06
    POSITIVE LOGITS
    }->
    0.11
    ew
    0.10
    tica
    0.10
    [__
    0.10
     Spread
    0.10
    -cond
    0.10
    HING
    0.10
    lash
    0.09
    _gp
    0.09
     echt
    0.09
    Activations Density 0.018%

    No Known Activations