© 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. 55726
    Prev
    Next
    INDEX
    Explanations

    alternatives to medications or costly treatments

    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
    ander
    -0.07
    identified
    -0.07
    aise
    -0.07
     Kitt
    -0.07
    rea
    -0.07
    æĮĩ
    -0.07
     suit
    -0.07
     blocked
    -0.07
     Urb
    -0.07
    pickup
    -0.06
    POSITIVE LOGITS
     resort
    0.17
     alternatives
    0.14
     Resort
    0.13
     Alternative
    0.13
     alternative
    0.13
     cheaper
    0.13
     costly
    0.12
     Spare
    0.12
     cost
    0.12
     lieu
    0.12
    Activations Density 0.184%

    No Known Activations