© 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. 2789
    Prev
    Next
    INDEX
    Explanations

    treat the

    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
    roc
    -0.10
    brook
    -0.09
    .pl
    -0.09
    æĺĵ
    -0.09
    dee
    -0.08
    éļ
    -0.08
     tq
    -0.08
     uptime
    -0.08
     decimal
    -0.08
    ÑģÑĤи
    -0.08
    POSITIVE LOGITS
     each
    0.10
     themselves
    0.09
    cken
    0.09
    each
    0.09
    cin
    0.08
     EACH
    0.08
     yourselves
    0.08
     datum
    0.08
     himself
    0.08
    å¾ħ
    0.08
    Activations Density 0.249%

    No Known Activations