© 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. 54611
    Prev
    Next
    INDEX
    Explanations

    margaret or margarine

    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
    ly
    -0.09
    ving
    -0.08
     Pra
    -0.08
     Gee
    -0.08
    ron
    -0.08
     giov
    -0.08
    deep
    -0.08
    renc
    -0.08
    lets
    -0.08
     Bian
    -0.08
    POSITIVE LOGITS
    /do
    0.09
    ity
    0.09
    ens
    0.09
    å¡
    0.09
    asz
    0.09
     Hague
    0.09
     Griff
    0.09
    TY
    0.09
    ar
    0.09
    OA
    0.08
    Activations Density 0.005%

    No Known Activations