© 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. 3736
    Prev
    Next
    INDEX
    Explanations

    in the

    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
    });↵↵↵↵
    -0.09
     Kil
    -0.09
     begged
    -0.09
     haste
    -0.09
     fend
    -0.08
    permalink
    -0.08
     coma
    -0.08
     Primitive
    -0.08
     front
    -0.08
     convenient
    -0.08
    POSITIVE LOGITS
     terms
    0.09
     light
    0.09
     LIGHT
    0.08
    swer
    0.08
    ourses
    0.08
     cases
    0.08
     ways
    0.08
    GES
    0.08
    -pages
    0.08
     Pang
    0.08
    Activations Density 0.245%

    No Known Activations