© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 571
    Prev
    Next
    INDEX
    Explanations

    progress and insight

    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
     iss
    -0.11
    esta
    -0.11
    -produced
    -0.10
    ANS
    -0.10
    ori
    -0.10
     chatt
    -0.10
    'user
    -0.10
    /ne
    -0.10
    'value
    -0.09
     Ook
    -0.09
    POSITIVE LOGITS
     for
    0.12
     regarding
    0.11
     against
    0.11
     towards
    0.11
     on
    0.11
     toward
    0.11
     from
    0.10
     between
    0.10
     apl
    0.10
     to
    0.09
    Activations Density 2.981%

    No Known Activations