© 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. 8505
    Prev
    Next
    INDEX
    Explanations

    patients with

    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
    inel
    -0.09
    inea
    -0.09
    hani
    -0.08
    inya
    -0.08
    że
    -0.08
    amped
    -0.08
    indo
    -0.08
    atr
    -0.08
    cate
    -0.08
     Candle
    -0.08
    POSITIVE LOGITS
     versus
    0.10
     vs
    0.10
     humans
    0.09
     Eisen
    0.09
     Bord
    0.09
     humanity
    0.09
     Fo
    0.08
     distinctions
    0.08
    -vs
    0.08
     differentiate
    0.08
    Activations Density 0.557%

    No Known Activations