© 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. 1608
    Prev
    Next
    INDEX
    Explanations

    connecting words or linking phrases

    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
    alam
    -0.08
    alm
    -0.08
    abal
    -0.08
     /^(
    -0.07
     doGet
    -0.07
     -->↵↵↵
    -0.07
    lyn
    -0.07
    alfa
    -0.07
    alla
    -0.07
    +offset
    -0.07
    POSITIVE LOGITS
     Ãĥ
    0.09
     likewise
    0.09
    &B
    0.09
    ÃĤ
    0.09
     ÂŃ
    0.09
    other
    0.08
    ÂŃt
    0.08
     meanwhile
    0.08
     ALSO
    0.08
    &type
    0.08
    Activations Density 2.407%

    No Known Activations