© 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. 3556
    Prev
    Next
    INDEX
    Explanations

    known for properties or descriptions

    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
    bout
    -0.11
     know
    -0.09
     about
    -0.08
    knowledge
    -0.08
     bout
    -0.08
    /k
    -0.08
     kennen
    -0.08
    know
    -0.08
     knowledge
    -0.08
     knew
    -0.07
    POSITIVE LOGITS
    ums
    0.13
    riot
    0.11
    ì¹ĺ
    0.11
    uche
    0.11
     Freak
    0.10
    yi
    0.10
    -Th
    0.10
     misc
    0.10
    eri
    0.10
    overe
    0.10
    Activations Density 0.079%

    No Known Activations