© 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. 8644
    Prev
    Next
    INDEX
    Explanations

    nearing or being at a conclusion

    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
     Esper
    -0.09
    lingen
    -0.08
    ibel
    -0.08
    ilik
    -0.08
    onas
    -0.08
    QP
    -0.07
     Patch
    -0.07
     GRE
    -0.07
    MOOTH
    -0.07
    Doc
    -0.07
    POSITIVE LOGITS
     nearing
    0.11
    iman
    0.10
     Stage
    0.10
    Lim
    0.10
     stage
    0.10
     puberty
    0.09
     maturity
    0.09
     matures
    0.09
     crisis
    0.09
     stages
    0.09
    Activations Density 0.299%

    No Known Activations