© 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. 8574
    Prev
    Next
    INDEX
    Explanations

    followed by comparative conjunctions or parameters

    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
    otos
    -0.10
     Correspond
    -0.09
     Rect
    -0.09
    ogle
    -0.09
    abet
    -0.09
     Kore
    -0.09
     Tradition
    -0.09
     Hammond
    -0.09
     penet
    -0.09
    perf
    -0.09
    POSITIVE LOGITS
     surprisingly
    0.10
     generally
    0.09
     disappoint
    0.09
     unsur
    0.08
     overwhelmingly
    0.08
     Mighty
    0.08
     Generally
    0.08
    <tbody
    0.08
     Institutes
    0.07
    oure
    0.07
    Activations Density 0.822%

    No Known Activations