© 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
    2. Olmo-3-1025-7B
    3. 16-RES-MATRYOSHKA-65K
    4. 2668
    Prev
    Next
    INDEX
    Explanations

    fixed newline output

    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
    IMP
    -0.09
    <|fim_middle|>
    -0.08
     typically
    -0.08
     normally
    -0.08
     essentially
    -0.08
     ordinarily
    -0.07
     accustomed
    -0.07
     intimately
    -0.07
     usually
    -0.07
     here
    -0.07
    POSITIVE LOGITS
    ableView
    0.11
    ,},↵
    0.10
     clearer
    0.10
     clearing
    0.10
     vandal
    0.09
    \E
    0.09
     cleared
    0.09
     wart
    0.09
     Clar
    0.09
     %↵↵
    0.09
    Activations Density 0.179%

    No Known Activations