© 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. 3809
    Prev
    Next
    INDEX
    Explanations

    code must

    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
    nero
    -0.09
     nails
    -0.09
    alar
    -0.08
     detach
    -0.08
     nail
    -0.08
    aan
    -0.08
     twilight
    -0.08
    ulla
    -0.08
    kle
    -0.08
     folds
    -0.08
    POSITIVE LOGITS
     ville
    0.09
     cand
    0.09
    iment
    0.09
    olle
    0.08
    _<
    0.08
    otes
    0.08
     Pou
    0.08
    ivas
    0.08
    usercontent
    0.08
    ìĨĮ
    0.08
    Activations Density 0.038%

    No Known Activations