© 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. 4191
    Prev
    Next
    INDEX
    Explanations

    focuses on limitations

    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
     traditionally
    -0.12
     historically
    -0.11
     Dj
    -0.09
    oriously
    -0.09
     Histor
    -0.09
    Trad
    -0.09
     moden
    -0.08
     lately
    -0.08
    trad
    -0.08
     nicknamed
    -0.08
    POSITIVE LOGITS
     focus
    0.12
     Focus
    0.11
    focus
    0.10
     focuses
    0.10
     focused
    0.10
     scope
    0.10
    çĦ
    0.10
     unspecified
    0.09
    Focus
    0.09
    focused
    0.09
    Activations Density 0.139%

    No Known Activations