© 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. 4211
    Prev
    Next
    INDEX
    Explanations

    seeing, relating, understanding, obtaining

    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
     explor
    -0.09
     Gunn
    -0.08
    Smart
    -0.08
     hastily
    -0.08
     Shaw
    -0.08
    ãĥ¥
    -0.08
    .ini
    -0.08
     UserController
    -0.08
    gee
    -0.08
     Britt
    -0.08
    POSITIVE LOGITS
     understanding
    0.10
     rationale
    0.10
     motivations
    0.10
     skepticism
    0.10
     notion
    0.10
     regard
    0.10
     philosophy
    0.09
     notions
    0.09
     reasons
    0.09
     thoughts
    0.09
    Activations Density 1.174%

    No Known Activations