© 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. 8587
    Prev
    Next
    INDEX
    Explanations

    story introduction

    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
    afe
    -0.09
    uning
    -0.09
     Oxygen
    -0.08
     Alma
    -0.08
     Yellow
    -0.08
     ima
    -0.08
    éĹ´
    -0.08
     Foot
    -0.08
    irse
    -0.08
    dh
    -0.08
    POSITIVE LOGITS
     told
    0.14
     arc
    0.13
    lines
    0.11
    -t
    0.10
    boards
    0.10
     arcs
    0.10
    arc
    0.10
    otal
    0.09
    atives
    0.09
    -unit
    0.09
    Activations Density 0.158%

    No Known Activations