© 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. 58082
    Prev
    Next
    INDEX
    Explanations

    or (2)

    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
    erg
    -0.09
    logging
    -0.08
    etc
    -0.08
    ra
    -0.08
    以ä¸Ĭ
    -0.08
    à¹Ī
    -0.08
    loggedin
    -0.08
     Guil
    -0.07
    Sharper
    -0.07
    ëł¥
    -0.07
    POSITIVE LOGITS
    /'
    0.08
     *,↵
    0.08
    Âł
    0.08
     ,↵↵
    0.08
    such
    0.08
    abcdefghijklmnopqrstuvwxyz
    0.08
    iversal
    0.08
     ,-
    0.08
    vro
    0.08
    official
    0.08
    Activations Density 0.013%

    No Known Activations