© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 1256
    Prev
    Next
    INDEX
    Explanations

    convicted, guilty, criminal, crimes

    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
    .ai
    -0.09
    iker
    -0.08
    /mod
    -0.08
     pencil
    -0.08
    chest
    -0.08
    tle
    -0.08
     bounding
    -0.07
     Disabled
    -0.07
    enet
    -0.07
    еÑĩ
    -0.07
    POSITIVE LOGITS
     crim
    0.12
     criminal
    0.12
    criminal
    0.10
     criminals
    0.10
     convictions
    0.10
     conviction
    0.10
    /legal
    0.10
    /pol
    0.10
     convict
    0.10
    iah
    0.09
    Activations Density 1.076%

    No Known Activations