© 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. 296
    Prev
    Next
    INDEX
    Explanations

    Scan/Mock/Search/PB/MD/SPR followed by result/response/item/field/source/bounds

    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
     Bliss
    -0.11
    اد
    -0.09
     Fee
    -0.09
     Others
    -0.09
     upstairs
    -0.09
    llib
    -0.09
     hardly
    -0.09
     Canal
    -0.09
    BufferSize
    -0.08
     haute
    -0.08
    POSITIVE LOGITS
    azel
    0.09
     Station
    0.08
    .types
    0.08
     metic
    0.08
    [ii
    0.08
     gamm
    0.08
    GenerationStrategy
    0.07
    imen
    0.07
    .objects
    0.07
    emodel
    0.07
    Activations Density 1.356%

    No Known Activations