© 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. 1060
    Prev
    Next
    INDEX
    Explanations

    legal roles and names followed by possessives

    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
     ensued
    -0.10
     merciless
    -0.10
    oster
    -0.10
     condemning
    -0.10
     dawn
    -0.09
     enforcing
    -0.09
     superiority
    -0.09
    orno
    -0.09
     condemn
    -0.09
    cue
    -0.08
    POSITIVE LOGITS
    ’s
    0.12
    's
    0.12
     himself
    0.11
     voluntarily
    0.10
    /respond
    0.09
    /my
    0.09
     living
    0.09
     receiving
    0.09
     whose
    0.08
     psyche
    0.08
    Activations Density 1.865%

    No Known Activations