© 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. 54330
    Prev
    Next
    INDEX
    Explanations

    protecting secrets and access

    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
    .Ma
    -0.09
     Revenge
    -0.09
     faults
    -0.09
    fault
    -0.09
    hausen
    -0.09
    .Est
    -0.09
     monitors
    -0.09
    chaft
    -0.09
     launching
    -0.08
     statistics
    -0.08
    POSITIVE LOGITS
     protecting
    0.14
     protection
    0.13
     protects
    0.12
     protect
    0.12
    protect
    0.12
    Protected
    0.11
     protective
    0.11
    Protect
    0.10
     protected
    0.10
     Protected
    0.10
    Activations Density 0.006%

    No Known Activations