© 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. 2715
    Prev
    Next
    INDEX
    Explanations

    fight, defend, protect, save

    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
     provocative
    -0.10
    stad
    -0.10
    PHA
    -0.09
     frankfurt
    -0.09
     controvers
    -0.09
    aucoup
    -0.09
    fly
    -0.09
    SEN
    -0.09
    xed
    -0.09
     snap
    -0.09
    POSITIVE LOGITS
     defending
    0.18
     defend
    0.17
     protecting
    0.14
     defence
    0.14
     defense
    0.14
     protector
    0.13
     protect
    0.13
     defenders
    0.13
     defended
    0.13
     fight
    0.13
    Activations Density 0.262%

    No Known Activations