© 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. 787
    Prev
    Next
    INDEX
    Explanations

    encounter a server busy

    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
     jm
    -0.11
     "...
    -0.10
     Adaptive
    -0.10
    mil
    -0.10
    chen
    -0.09
    anova
    -0.09
     familiar
    -0.09
    ints
    -0.09
     Foster
    -0.09
    uter
    -0.09
    POSITIVE LOGITS
    ilon
    0.08
     ange
    0.08
    ĥģ
    0.07
    âĢ¦↵↵↵
    0.07
    eve
    0.07
    OfYear
    0.07
    deaux
    0.07
    pson
    0.07
     >↵↵
    0.06
    ereo
    0.06
    Activations Density 0.844%

    No Known Activations