© 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. 57937
    Prev
    Next
    INDEX
    Explanations

    .b ib

    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
     charging
    -0.09
    ly
    -0.08
    antes
    -0.08
    OTH
    -0.08
     Leonard
    -0.08
    iding
    -0.08
     Charging
    -0.08
     shouts
    -0.08
     Tick
    -0.08
     adoption
    -0.08
    POSITIVE LOGITS
    WWW
    0.10
    warts
    0.09
    asan
    0.09
    hari
    0.09
    hir
    0.09
    peare
    0.09
    ÃŃs
    0.09
    idon
    0.09
    pend
    0.09
    anden
    0.08
    Activations Density 0.001%

    No Known Activations