© 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. 3492
    Prev
    Next
    INDEX
    Explanations

    benign, humane, sincere, or genuine

    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
     confidently
    -0.09
     Suff
    -0.09
     Vig
    -0.09
     vigil
    -0.09
     boldly
    -0.09
    omat
    -0.08
     resid
    -0.08
     impatient
    -0.08
    <>
    -0.08
     Matters
    -0.07
    POSITIVE LOGITS
     humane
    0.19
     benign
    0.18
     harmless
    0.17
     friendly
    0.17
     legitimate
    0.16
     sincerely
    0.16
     bene
    0.16
     genuine
    0.16
     redeem
    0.16
     honest
    0.15
    Activations Density 0.295%

    No Known Activations