© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 3741
    Prev
    Next
    INDEX
    Explanations

    en

    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
     ingenious
    -0.09
     seminal
    -0.08
     beautiful
    -0.08
     ne
    -0.07
     clever
    -0.07
     Bench
    -0.07
     stal
    -0.07
     tu
    -0.07
     cited
    -0.07
     bree
    -0.06
    POSITIVE LOGITS
    ardy
    0.10
     verz
    0.10
     hopefully
    0.10
     Doctor
    0.10
    urv
    0.10
     mich
    0.10
     myself
    0.09
     #__
    0.09
     Blank
    0.09
     Mojo
    0.09
    Activations Density 0.055%

    No Known Activations