© 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. 4304
    Prev
    Next
    INDEX
    Explanations

    next:

    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
    -0.13
     aver
    -0.11
    mvc
    -0.11
    imas
    -0.11
     teal
    -0.11
    alars
    -0.11
    ebb
    -0.11
    ccd
    -0.11
    ibur
    -0.11
    wie
    -0.11
    POSITIVE LOGITS
     logic
    0.08
     trend
    0.07
     earlier
    0.07
     pattern
    0.07
     Down
    0.07
     stimulation
    0.07
     previous
    0.06
     based
    0.06
    è§Ħ
    0.06
     stir
    0.06
    Activations Density 0.009%

    No Known Activations