© 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. 55497
    Prev
    Next
    INDEX
    Explanations

    process creation

    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
    thinkable
    -0.10
    ses
    -0.09
    ther
    -0.09
    coil
    -0.09
    utto
    -0.08
    >čč↵
    -0.08
    orie
    -0.08
    bolt
    -0.08
     champion
    -0.08
    ADS
    -0.08
    POSITIVE LOGITS
    rix
    0.08
    INTR
    0.08
    rift
    0.08
     brew
    0.08
    lah
    0.08
     amnesty
    0.08
    ãģķ
    0.08
    aket
    0.08
    :null
    0.07
     amer
    0.07
    Activations Density 0.033%

    No Known Activations