© 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. 837
    Prev
    Next
    INDEX
    Explanations

    medical history or diagnosis

    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
     thousands
    -0.10
     hundreds
    -0.08
    "path
    -0.08
     hopefully
    -0.08
    -Allow
    -0.08
     millions
    -0.08
    ialog
    -0.08
     wherever
    -0.08
    linger
    -0.08
     newSize
    -0.07
    POSITIVE LOGITS
     âī¥
    0.16
     household
    0.12
     either
    0.12
     âī¤
    0.11
     households
    0.11
     >=
    0.11
     category
    0.11
     classified
    0.11
     Gle
    0.10
     predefined
    0.10
    Activations Density 3.212%

    No Known Activations