© 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. 55073
    Prev
    Next
    INDEX
    Explanations

    of [classifier]

    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
     defer
    -0.08
    /lang
    -0.08
    imenti
    -0.08
    jang
    -0.08
     Sentinel
    -0.08
     accur
    -0.08
     sorts
    -0.08
    faf
    -0.08
     Bowman
    -0.08
    uze
    -0.07
    POSITIVE LOGITS
    esser
    0.11
     Reb
    0.09
    /dis
    0.09
     Tra
    0.09
    kle
    0.08
    ord
    0.08
    tra
    0.08
    uto
    0.08
    ounds
    0.08
    Tra
    0.08
    Activations Density 0.071%

    No Known Activations