© 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. 362
    Prev
    Next
    INDEX
    Explanations

    read out about give look consider

    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
    ducted
    -0.10
    ãĥĪ
    -0.10
     Macro
    -0.10
     unfortunately
    -0.10
     kond
    -0.09
    -highlight
    -0.09
    rad
    -0.09
    IRD
    -0.09
    byn
    -0.09
    bsite
    -0.09
    POSITIVE LOGITS
     yourself
    0.26
     yourselves
    0.24
     Yourself
    0.17
    ÑĤе
    0.16
     your
    0.15
    lah
    0.13
     carefully
    0.13
     bitte
    0.12
     thy
    0.12
     accordingly
    0.12
    Activations Density 1.513%

    No Known Activations