© 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. 1523
    Prev
    Next
    INDEX
    Explanations

    quantified categories or instances

    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
     stripslashes
    -0.08
    jar
    -0.08
    alk
    -0.07
     wherever
    -0.07
     FAR
    -0.07
     bem
    -0.07
     fare
    -0.07
    iller
    -0.07
     percentages
    -0.07
     SUCH
    -0.07
    POSITIVE LOGITS
     total
    0.17
     (!
    0.15
     altogether
    0.14
    total
    0.14
    -plus
    0.14
    /year
    0.13
     annually
    0.13
     EACH
    0.13
     Including
    0.13
     assorted
    0.13
    Activations Density 2.140%

    No Known Activations