© 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. 2508
    Prev
    Next
    INDEX
    Explanations

    emotional distress, death, injury, damages, breach

    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
     impartial
    -0.10
     transparency
    -0.09
     поÑĢ
    -0.08
     Ridge
    -0.08
    -dess
    -0.08
     Hope
    -0.08
    STAR
    -0.08
    apol
    -0.08
    overs
    -0.08
     voucher
    -0.08
    POSITIVE LOGITS
     damages
    0.12
     losses
    0.11
     Lost
    0.11
     Dam
    0.11
     lost
    0.11
    lost
    0.10
     DAMAGES
    0.09
     damaged
    0.09
    ett
    0.09
    dam
    0.09
    Activations Density 0.054%

    No Known Activations