© 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. 4183
    Prev
    Next
    INDEX
    Explanations

    in successive context

    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
     briefly
    -0.10
    ente
    -0.10
     ters
    -0.09
     midst
    -0.09
     action
    -0.08
    heim
    -0.08
     Older
    -0.08
    jar
    -0.08
    sep
    -0.08
    plevel
    -0.08
    POSITIVE LOGITS
    lj
    0.10
    rab
    0.10
    vor
    0.09
     intervals
    0.09
     ways
    0.09
    avec
    0.09
     Quint
    0.08
    rand
    0.08
     clandest
    0.08
     Aber
    0.08
    Activations Density 0.353%

    No Known Activations