© 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. 665
    Prev
    Next
    INDEX
    Explanations

    names and locations

    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
    (Locale
    -0.08
     Esp
    -0.07
     balanced
    -0.07
    TECT
    -0.07
    -bal
    -0.07
    bsp
    -0.07
     midfield
    -0.06
     efficiency
    -0.06
    balanced
    -0.06
     discipline
    -0.06
    POSITIVE LOGITS
    /original
    0.10
     infamous
    0.09
    azzi
    0.09
    (dead
    0.09
     famously
    0.09
    /single
    0.09
    orda
    0.08
    phem
    0.08
    !!.
    0.08
     gameOver
    0.08
    Activations Density 3.898%

    No Known Activations