© 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. 58840
    Prev
    Next
    INDEX
    Explanations

    crimes and offenses

    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
    san
    -0.09
     reperc
    -0.09
    isy
    -0.09
     neh
    -0.09
    iven
    -0.09
     Linden
    -0.09
     Stub
    -0.09
    idos
    -0.09
     frightening
    -0.08
    mer
    -0.08
    POSITIVE LOGITS
    erta
    0.08
    udu
    0.08
     span
    0.08
     damn
    0.08
    oft
    0.08
     Suz
    0.08
    inkel
    0.08
    assi
    0.08
    geist
    0.08
    unk
    0.08
    Activations Density 0.002%

    No Known Activations