© 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. 8630
    Prev
    Next
    INDEX
    Explanations

    other followed by noun

    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
    ften
    -0.10
    åĪ«
    -0.09
    oola
    -0.09
    Ħ
    -0.09
    kke
    -0.08
     ado
    -0.08
    emann
    -0.08
     Pussy
    -0.08
    odom
    -0.08
    scheduled
    -0.08
    POSITIVE LOGITS
     Patterson
    0.10
    们
    0.08
    habit
    0.08
     taraf
    0.08
     sö
    0.08
    li
    0.08
    ewn
    0.07
    ness
    0.07
    hood
    0.07
    ikon
    0.07
    Activations Density 0.095%

    No Known Activations