© 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. 128
    Prev
    Next
    INDEX
    Explanations

    numbers followed by punctuation

    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
    ationally
    -0.09
    elan
    -0.09
     verdad
    -0.08
     Tate
    -0.08
     Gecko
    -0.08
     -,
    -0.08
     Marin
    -0.08
    ÑĢаÑĤ
    -0.08
    oley
    -0.08
     Trident
    -0.08
    POSITIVE LOGITS
    <|fim_suffix|>
    0.09
     zi
    0.08
    ibold
    0.07
     fine
    0.07
    wo
    0.07
    ji
    0.07
     opc
    0.07
    Cha
    0.07
    plan
    0.07
     vak
    0.07
    Activations Density 0.779%

    No Known Activations