© 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. 55242
    Prev
    Next
    INDEX
    Explanations

    beyond norm

    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
     Ord
    -0.09
     harmless
    -0.09
    æ²»
    -0.09
     insignificant
    -0.08
     fortunate
    -0.08
     upright
    -0.08
    ound
    -0.08
    rede
    -0.08
    Shown
    -0.08
    AGAIN
    -0.08
    POSITIVE LOGITS
     extra
    0.18
     Extra
    0.15
     excess
    0.15
     unusual
    0.14
    Extra
    0.13
     unconventional
    0.13
     beyond
    0.13
     extras
    0.13
     Extras
    0.13
    extra
    0.13
    Activations Density 0.218%

    No Known Activations