© 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. 52
    Prev
    Next
    INDEX
    Explanations

    Defensive words and endings

    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
    orro
    -0.10
    lder
    -0.10
     Âł Âł
    -0.10
    ling
    -0.09
    adar
    -0.09
     Âł
    -0.09
    yme
    -0.09
    ock
    -0.08
     Âł Âł Âł Âł
    -0.08
    ç¨ĭ
    -0.08
    POSITIVE LOGITS
    ively
    0.13
    ivre
    0.11
    vely
    0.10
    ive
    0.10
    ining
    0.10
    iate
    0.10
    iners
    0.10
    mil
    0.10
    loor
    0.09
    iveness
    0.09
    Activations Density 0.514%

    No Known Activations