© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 1968
    Prev
    Next
    INDEX
    Explanations

    v. in legal citations

    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
     materially
    -0.09
     pal
    -0.08
    ulpt
    -0.07
    online
    -0.07
    ext
    -0.07
    neapolis
    -0.07
     Span
    -0.07
     condition
    -0.07
     Sutton
    -0.07
    t
    -0.07
    POSITIVE LOGITS
     rivals
    0.10
     Transcript
    0.10
    ioso
    0.10
    aea
    0.10
    ardi
    0.09
    dera
    0.09
    EFR
    0.09
    rafted
    0.09
    mlx
    0.09
     challenger
    0.09
    Activations Density 0.324%

    No Known Activations