© 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. 55879
    Prev
    Next
    INDEX
    Explanations

    code 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
    _ins
    -0.11
     Trident
    -0.10
     verde
    -0.10
     Spell
    -0.10
    atak
    -0.10
    rios
    -0.10
     Trev
    -0.09
    ricks
    -0.09
    olas
    -0.09
    .setUp
    -0.09
    POSITIVE LOGITS
     hop
    0.07
    rottle
    0.07
     blackout
    0.07
    iesel
    0.07
    orate
    0.07
    modifiable
    0.07
     gor
    0.07
     Sol
    0.07
     vending
    0.07
     Victoria
    0.07
    Activations Density 0.005%

    No Known Activations