© 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. 54334
    Prev
    Next
    INDEX
    Explanations

    descriptive labels before content

    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
    اء
    -0.11
    ']]],↵
    -0.10
     endregion
    -0.10
     zip
    -0.09
    ,↵↵↵
    -0.09
    ivr
    -0.09
    WEEN
    -0.09
     Zip
    -0.09
     skl
    -0.09
     Wich
    -0.09
    POSITIVE LOGITS
    /photo
    0.08
     pore
    0.08
    atches
    0.07
    acher
    0.07
    TER
    0.07
     Metro
    0.07
    gst
    0.07
    orth
    0.07
    æīĵ
    0.07
     rec
    0.07
    Activations Density 0.001%

    No Known Activations