© 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. 2289
    Prev
    Next
    INDEX
    Explanations

    if 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
     bé
    -0.11
    اد
    -0.11
    EOS
    -0.11
     badly
    -0.11
     attempt
    -0.11
     desperate
    -0.10
     hei
    -0.10
    oland
    -0.10
     Investigation
    -0.10
    esus
    -0.10
    POSITIVE LOGITS
     somehow
    0.09
     somew
    0.09
     avoided
    0.08
    inh
    0.07
    uto
    0.07
     persuaded
    0.06
     feature
    0.06
     Du
    0.06
    wich
    0.06
    ÃŃs
    0.06
    Activations Density 0.231%

    No Known Activations