© 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. 3083
    Prev
    Next
    INDEX
    Explanations

    repurposed or old items

    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
    usher
    -0.09
     symbolic
    -0.09
     Habit
    -0.08
    pon
    -0.08
     unic
    -0.08
     facilit
    -0.08
    jav
    -0.07
     coded
    -0.07
     companion
    -0.07
    /providers
    -0.07
    POSITIVE LOGITS
     abandoned
    0.16
     leftover
    0.15
     reuse
    0.15
     discarded
    0.14
     unused
    0.14
     rep
    0.14
     turned
    0.13
     reused
    0.13
    -turned
    0.13
     recycled
    0.13
    Activations Density 0.412%

    No Known Activations