© 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. 8374
    Prev
    Next
    INDEX
    Explanations

    cross-examination or questioning

    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
    antee
    -0.11
    alo
    -0.09
    gran
    -0.09
     Kear
    -0.09
     gro
    -0.09
    ï¿
    -0.09
    reece
    -0.09
    landing
    -0.09
    junction
    -0.09
    rike
    -0.08
    POSITIVE LOGITS
     hid
    0.08
     transit
    0.07
     Inter
    0.07
    Designed
    0.07
     sle
    0.07
    erner
    0.07
     Bers
    0.07
    র
    0.07
     Wik
    0.07
     Suites
    0.07
    Activations Density 0.026%

    No Known Activations