© 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. 4748
    Prev
    Next
    INDEX
    Explanations

    double-blind, double-faced, double-check

    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
    Not in Any Lists

    No Comments

    Negative Logits
     tail
    -0.08
    ÃŃv
    -0.07
    im
    -0.06
     elev
    -0.06
     tails
    -0.06
    il
    -0.06
    iet
    -0.06
    imensional
    -0.06
     Misc
    -0.06
     elevation
    -0.06
    POSITIVE LOGITS
    .parseDouble
    0.19
    ts
    0.15
     entend
    0.14
    -blind
    0.13
    .infinity
    0.13
     Trouble
    0.13
    tte
    0.12
    .NaN
    0.12
    -check
    0.12
    ogh
    0.12
    Activations Density 0.090%

    No Known Activations