© 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. 61590
    Prev
    Next
    INDEX
    Explanations

    as [adverb] as possible

    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
     anything
    -0.10
     contrario
    -0.10
    acas
    -0.10
     Pemb
    -0.10
     spare
    -0.10
     oppos
    -0.09
     sparing
    -0.09
     Bri
    -0.09
    lush
    -0.09
    çļ
    -0.09
    POSITIVE LOGITS
     overse
    0.08
    å¾
    0.07
    ento
    0.07
    iner
    0.07
     amusing
    0.07
    olo
    0.07
    ann
    0.07
     easily
    0.06
    eka
    0.06
    tent
    0.06
    Activations Density 0.008%

    No Known Activations