© 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. 276
    Prev
    Next
    INDEX
    Explanations

    violated, deprived, unfair, improper, unlawfully

    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
    ambio
    -0.09
    ihan
    -0.09
     unaffected
    -0.09
     neatly
    -0.09
     aster
    -0.08
     absor
    -0.08
     Rossi
    -0.08
     absorbing
    -0.08
     extremism
    -0.08
     overd
    -0.08
    POSITIVE LOGITS
     allegedly
    0.13
     unfair
    0.12
     promised
    0.11
     mist
    0.10
     Practices
    0.10
     practices
    0.10
     improper
    0.10
     unfairly
    0.10
     incompetent
    0.10
     biased
    0.09
    Activations Density 0.753%

    No Known Activations