© 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. 621
    Prev
    Next
    INDEX
    Explanations

    code delimiters or prefixes

    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
    anced
    -0.09
    itant
    -0.09
     made
    -0.09
    [::-
    -0.09
     semi
    -0.09
     Elis
    -0.09
     inter
    -0.08
    -ch
    -0.08
    otte
    -0.08
     pleading
    -0.08
    POSITIVE LOGITS
     siz
    0.11
    _argument
    0.11
    psilon
    0.10
    ?url
    0.09
     ={↵
    0.09
    ocr
    0.09
    elves
    0.08
     bureaucr
    0.08
    pose
    0.08
     telefon
    0.08
    Activations Density 0.395%

    No Known Activations