© 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. 4125
    Prev
    Next
    INDEX
    Explanations

    requests for information or subpoenas

    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
    .herokuapp
    -0.11
    -cancel
    -0.11
    chan
    -0.11
    stakes
    -0.11
    apse
    -0.11
     advertis
    -0.11
    kart
    -0.11
    cents
    -0.11
    heck
    -0.11
    aler
    -0.11
    POSITIVE LOGITS
     subpoena
    0.14
     requested
    0.14
     request
    0.13
     Request
    0.12
     requests
    0.12
     Requests
    0.10
    requested
    0.10
     requester
    0.10
     requesting
    0.10
     Access
    0.09
    Activations Density 0.110%

    No Known Activations