© 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. 3362
    Prev
    Next
    INDEX
    Explanations

    one of the

    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
     incarnation
    -0.10
    stuff
    -0.09
     amongst
    -0.09
     opener
    -0.09
    .deserialize
    -0.09
     contender
    -0.09
     stereotype
    -0.09
     déf
    -0.08
     fragmentation
    -0.08
     weaponry
    -0.08
    POSITIVE LOGITS
     versions
    0.12
     setups
    0.11
     times
    0.11
     environments
    0.10
    änn
    0.09
    versions
    0.08
     lifestyles
    0.08
     educ
    0.08
    rias
    0.08
     halves
    0.08
    Activations Density 0.223%

    No Known Activations