© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 8378
    Prev
    Next
    INDEX
    Explanations

    names ending in s or x

    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
    ullo
    -0.10
    cod
    -0.08
     infiltration
    -0.08
    -origin
    -0.08
    PIX
    -0.08
    .ready
    -0.08
     Abed
    -0.08
    ibil
    -0.08
    wal
    -0.08
    apas
    -0.08
    POSITIVE LOGITS
     meanwhile
    0.15
     again
    0.13
     disappears
    0.12
     disappear
    0.12
     dies
    0.12
     die
    0.12
     died
    0.12
     continues
    0.11
     continue
    0.10
     continued
    0.10
    Activations Density 0.072%

    No Known Activations