© 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. 3643
    Prev
    Next
    INDEX
    Explanations

    almost always / never

    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
    ola
    -0.09
     roughly
    -0.09
    led
    -0.09
    aim
    -0.08
     Rough
    -0.08
     Ful
    -0.08
     ener
    -0.07
     Bloody
    -0.07
    google
    -0.07
     Mustang
    -0.07
    POSITIVE LOGITS
     exclusively
    0.12
    oct
    0.10
    istar
    0.09
     entirely
    0.09
     vu
    0.09
    ago
    0.09
    elta
    0.09
    iska
    0.09
    oa
    0.08
     excessively
    0.08
    Activations Density 0.062%

    No Known Activations