© 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. 57061
    Prev
    Next
    INDEX
    Explanations

    symptoms and 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
     ju
    -0.11
    rup
    -0.11
     Crush
    -0.10
     Needle
    -0.10
    andles
    -0.10
    gor
    -0.10
    adden
    -0.10
    CLUDING
    -0.10
     nulla
    -0.10
    /connect
    -0.10
    POSITIVE LOGITS
     Symptoms
    0.09
     treatment
    0.09
     symptoms
    0.09
     typically
    0.08
     Treatment
    0.08
     treatments
    0.08
     Causes
    0.08
     causes
    0.07
    YM
    0.07
     prescribed
    0.07
    Activations Density 0.074%

    No Known Activations