© 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. 54634
    Prev
    Next
    INDEX
    Explanations

    ordering, ranking, second, third

    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
     again
    -0.11
    toi
    -0.10
     Again
    -0.10
    (es
    -0.09
    ]+$
    -0.09
    ew
    -0.09
    Again
    -0.09
    র
    -0.08
    toc
    -0.08
     granny
    -0.08
    POSITIVE LOGITS
    ieux
    0.09
    tha
    0.08
    **č↵
    0.08
     folds
    0.08
     asÃŃ
    0.08
     enjoying
    0.08
    iples
    0.08
    recht
    0.08
    frica
    0.07
     Rise
    0.07
    Activations Density 0.021%

    No Known Activations