© 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. 55397
    Prev
    Next
    INDEX
    Explanations

    numbers followed by x or -D

    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
    .ua
    -0.10
    velle
    -0.10
    abad
    -0.09
    swith
    -0.09
    akhir
    -0.09
    AAD
    -0.09
     Pale
    -0.08
    ailable
    -0.08
    yntax
    -0.08
    .getvalue
    -0.08
    POSITIVE LOGITS
     dre
    0.08
     plateau
    0.08
    dre
    0.08
     meaningful
    0.08
     Donald
    0.08
     cri
    0.08
    ŀ
    0.07
     Gra
    0.07
     sha
    0.07
    usa
    0.07
    Activations Density 0.001%

    No Known Activations