© 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. 3851
    Prev
    Next
    INDEX
    Explanations

    United States District Court

    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
    ains
    -0.08
    rado
    -0.08
     entrusted
    -0.08
     Association
    -0.07
    dart
    -0.07
    allee
    -0.07
     padr
    -0.07
     Tradition
    -0.07
    .until
    -0.07
     attendees
    -0.07
    POSITIVE LOGITS
    ovel
    0.10
    olen
    0.09
    propri
    0.09
    unj
    0.09
    ots
    0.09
     doorstep
    0.09
    otty
    0.08
    opa
    0.08
    uni
    0.08
    osit
    0.08
    Activations Density 0.074%

    No Known Activations