© 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. 8528
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    oug
    -0.07
     Erica
    -0.07
    aden
    -0.07
    ogi
    -0.07
    oba
    -0.07
     Oliv
    -0.07
    .edit
    -0.07
     flat
    -0.07
    udas
    -0.07
    -ch
    -0.07
    POSITIVE LOGITS
     DAMAGE
    0.11
    _imp
    0.11
     permanent
    0.10
     Permanent
    0.10
     eventual
    0.10
    std
    0.10
     Feinstein
    0.10
     (âĪ
    0.09
    permanent
    0.09
    orest
    0.09
    Activations Density 0.000%

    No Known Activations