© 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. 4355
    Prev
    Next
    INDEX
    Explanations

    Why questions

    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
     why
    -0.10
    l
    -0.09
    ona
    -0.09
    why
    -0.08
    lies
    -0.08
     Why
    -0.08
    VB
    -0.08
    Why
    -0.08
    ocracy
    -0.07
    lek
    -0.07
    POSITIVE LOGITS
    eous
    0.12
    /how
    0.12
    eil
    0.11
    te
    0.11
    ea
    0.10
    iao
    0.10
    ti
    0.10
    zas
    0.10
    ubits
    0.10
    tile
    0.10
    Activations Density 0.123%

    No Known Activations