© 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. 4517
    Prev
    Next
    INDEX
    Explanations

    click, drag, or swipe

    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
     automat
    -0.10
    kept
    -0.10
    anus
    -0.10
    ail
    -0.09
    autom
    -0.09
     pack
    -0.09
     Yesterday
    -0.09
    abis
    -0.09
     packed
    -0.09
     automatically
    -0.08
    POSITIVE LOGITS
     input
    0.10
    .touch
    0.10
    appings
    0.09
    è¾ĵåħ¥
    0.09
     manipulation
    0.09
     gestures
    0.09
     flick
    0.09
     Accepted
    0.09
    lick
    0.08
     Stanley
    0.08
    Activations Density 0.592%

    No Known Activations