© 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. 2569
    Prev
    Next
    INDEX
    Explanations

    identi

    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
     Stanton
    -0.09
    ]){
    -0.09
     saf
    -0.08
    stant
    -0.08
    pes
    -0.08
    arn
    -0.08
     tamp
    -0.08
    oe
    -0.07
     lucr
    -0.07
    orida
    -0.07
    POSITIVE LOGITS
    ccb
    0.10
    isoft
    0.10
    ilities
    0.10
    igator
    0.10
    ventus
    0.09
    -extra
    0.09
     forward
    0.09
    acro
    0.09
    rolled
    0.09
    ffa
    0.09
    Activations Density 0.282%

    No Known Activations