© 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. 54558
    Prev
    Next
    INDEX
    Explanations

    magic, spells, curses

    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
     resembl
    -0.09
    -dialog
    -0.09
     madness
    -0.09
    tera
    -0.09
     periodically
    -0.09
     Olivier
    -0.09
     synchronized
    -0.09
    variably
    -0.08
    .www
    -0.08
     symb
    -0.08
    POSITIVE LOGITS
    kie
    0.11
     technique
    0.09
     sealing
    0.09
    aine
    0.09
    èĮ
    0.09
     misuse
    0.09
     requested
    0.09
     request
    0.08
    313
    0.08
     suburban
    0.08
    Activations Density 0.031%

    No Known Activations