© 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
    2. Olmo-3-1025-7B
    3. 16-RES-MATRYOSHKA-65K
    4. 58209
    Prev
    Next
    INDEX
    Explanations

    "Read" or file changes

    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
    ubar
    -0.09
    QN
    -0.09
     Dion
    -0.09
    uci
    -0.09
    asto
    -0.09
     Dort
    -0.09
     calend
    -0.08
     Bennett
    -0.08
     Abbott
    -0.08
    serter
    -0.08
    POSITIVE LOGITS
     convention
    0.09
    ee
    0.08
    âĢİ
    0.08
     Spear
    0.08
    posted
    0.08
    cco
    0.08
     Board
    0.07
    ra
    0.07
    pa
    0.07
     Jeff
    0.07
    Activations Density 0.003%

    No Known Activations