© 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. 3540
    Prev
    Next
    INDEX
    Explanations

    proposed empirical model

    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
    arts
    -0.10
    Credits
    -0.10
     waive
    -0.09
     Credits
    -0.09
    ikh
    -0.09
    hei
    -0.09
    ;q
    -0.09
    ?[
    -0.09
    agan
    -0.09
     Ord
    -0.09
    POSITIVE LOGITS
     successfully
    0.11
    enger
    0.09
     clever
    0.08
     “âĢ¦
    0.08
    iasm
    0.08
    enga
    0.08
     Cle
    0.08
    ãĥĵ
    0.08
    otes
    0.08
    Discussion
    0.08
    Activations Density 0.108%

    No Known Activations