© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 3178
    Prev
    Next
    INDEX
    Explanations

    negligence or fault

    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
     Threat
    -0.10
     threatened
    -0.09
     parallel
    -0.08
    Sensitive
    -0.08
     successful
    -0.08
    anel
    -0.08
     Early
    -0.07
     paired
    -0.07
     sensitive
    -0.07
     interpre
    -0.07
    POSITIVE LOGITS
     negligence
    0.15
     negligent
    0.14
     blaming
    0.14
    -errors
    0.12
     neglig
    0.12
     culp
    0.12
     blame
    0.12
     defective
    0.12
     careless
    0.11
     fault
    0.11
    Activations Density 0.082%

    No Known Activations