© 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. 1010
    Prev
    Next
    INDEX
    Explanations

    -bolic/-omyk

    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
    ekte
    -0.10
     Britt
    -0.09
    gni
    -0.09
     resting
    -0.09
    -----------č↵
    -0.09
     magn
    -0.09
     Angels
    -0.09
    ensem
    -0.09
    ouri
    -0.09
     før
    -0.09
    POSITIVE LOGITS
     Markus
    0.07
     ordin
    0.07
     Nab
    0.07
    wick
    0.07
     correspond
    0.07
     Fowler
    0.06
     Ring
    0.06
    ussen
    0.06
    аз
    0.06
     Weg
    0.06
    Activations Density 0.744%

    No Known Activations