© 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. 2502
    Prev
    Next
    INDEX
    Explanations

    summary, needs, name, used, iteration, falls, if, understanding, modify

    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
    еÑĩ
    -0.08
    richt
    -0.08
    Pres
    -0.08
    zin
    -0.07
    art
    -0.07
     transports
    -0.07
    quia
    -0.07
    atal
    -0.07
     Pres
    -0.06
    sch
    -0.06
    POSITIVE LOGITS
    aza
    0.14
     coined
    0.10
     simpl
    0.09
    .KEY
    0.09
     examples
    0.09
     recent
    0.09
    erne
    0.09
    Bạn
    0.09
     unpublished
    0.09
    (patch
    0.09
    Activations Density 1.085%

    No Known Activations