© 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. 54727
    Prev
    Next
    INDEX
    Explanations

    good news is

    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
    odia
    -0.10
     brilliance
    -0.10
    rieve
    -0.10
     Listings
    -0.10
    rect
    -0.09
     Alg
    -0.09
     thu
    -0.09
    Py
    -0.09
    QP
    -0.09
    chin
    -0.09
    POSITIVE LOGITS
    yan
    0.08
    ARS
    0.08
    FW
    0.07
     propositions
    0.07
    Für
    0.07
    enko
    0.07
     reassuring
    0.07
    eros
    0.06
     breathe
    0.06
    vis
    0.06
    Activations Density 0.013%

    No Known Activations