© 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. 238
    Prev
    Next
    INDEX
    Explanations

    code elements and special syntax

    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
    ³³³³³³³
    -0.12
    ³³³³
    -0.12
    al
    -0.11
    ³³
    -0.11
    vor
    -0.11
    ³³³³³³³³
    -0.11
    Âł
    -0.10
    -0.10
    rus
    -0.10
    ³³³
    -0.10
    POSITIVE LOGITS
     Mack
    0.08
    ije
    0.08
    ern
    0.08
    omit
    0.08
    acle
    0.08
     hog
    0.07
    ıè¿°
    0.07
    zzo
    0.07
    Trace
    0.07
    eg
    0.07
    Activations Density 0.175%

    No Known Activations