© 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. 3033
    Prev
    Next
    INDEX
    Explanations

    crime victims and perpetrators

    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
     Official
    -0.10
    =%.
    -0.09
     presum
    -0.09
    -signed
    -0.09
    haft
    -0.09
     grounding
    -0.08
    Official
    -0.08
     Medi
    -0.08
     fatto
    -0.08
     impatient
    -0.08
    POSITIVE LOGITS
     terrified
    0.10
     scream
    0.10
    /report
    0.09
     appreh
    0.09
     overpower
    0.09
    utions
    0.09
     vandal
    0.09
     trembling
    0.09
     intrusion
    0.09
     duct
    0.09
    Activations Density 0.126%

    No Known Activations