© 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. 1379
    Prev
    Next
    INDEX
    Explanations

    legal argumentation and justification

    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
     nowadays
    -0.12
     Usually
    -0.11
     usually
    -0.11
     correspondent
    -0.11
     often
    -0.10
    nod
    -0.10
     Often
    -0.10
     lately
    -0.10
    anes
    -0.10
    Often
    -0.10
    POSITIVE LOGITS
     grounds
    0.11
     retro
    0.10
     merit
    0.09
     merits
    0.09
     nexus
    0.08
     justified
    0.08
     second
    0.08
     retrospect
    0.08
     qualifies
    0.08
     counts
    0.08
    Activations Density 0.346%

    No Known Activations