© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 3984
    Prev
    Next
    INDEX
    Explanations

    drawing conclusions

    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
    éĩı
    -0.10
    acy
    -0.09
    iment
    -0.09
    /items
    -0.09
    uteur
    -0.09
    rios
    -0.09
    ilo
    -0.08
    atz
    -0.08
    iera
    -0.08
    uff
    -0.08
    POSITIVE LOGITS
     conclusion
    0.09
     drawn
    0.09
    er
    0.09
    ged
    0.09
    amm
    0.09
    aram
    0.08
     conclusions
    0.08
    tero
    0.08
    lications
    0.08
    imin
    0.08
    Activations Density 0.023%

    No Known Activations