© 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. 107
    Prev
    Next
    INDEX
    Explanations

    a key component

    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
     reign
    -0.09
     notions
    -0.09
     range
    -0.08
    ecc
    -0.08
    burger
    -0.08
     ranges
    -0.08
     attendant
    -0.08
    ran
    -0.08
    successful
    -0.08
     array
    -0.08
    POSITIVE LOGITS
     harb
    0.16
     stepping
    0.16
     part
    0.15
     testament
    0.15
     gateway
    0.14
     cornerstone
    0.13
     reflection
    0.13
     conduit
    0.13
     source
    0.13
     staple
    0.13
    Activations Density 2.062%

    No Known Activations