© 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. 1111
    Prev
    Next
    INDEX
    Explanations

    secure / safety / security

    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
    ather
    -0.11
    istributor
    -0.10
    AndPassword
    -0.10
    abin
    -0.10
    dish
    -0.10
    lam
    -0.10
     Pam
    -0.10
     Tide
    -0.10
     pragma
    -0.10
    waiting
    -0.10
    POSITIVE LOGITS
     against
    0.14
    ty
    0.11
    /security
    0.10
    heits
    0.10
    Against
    0.10
     measures
    0.10
    against
    0.10
     Against
    0.09
     measure
    0.09
    heit
    0.09
    Activations Density 1.419%

    No Known Activations