© 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. 677
    Prev
    Next
    INDEX
    Explanations

    crime, conspiracy, terrorism

    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
     Ion
    -0.09
    pend
    -0.09
     Rescue
    -0.09
    idas
    -0.08
    uez
    -0.08
    .pt
    -0.08
     slander
    -0.08
     spanking
    -0.08
     slapped
    -0.08
    assadors
    -0.08
    POSITIVE LOGITS
     targeting
    0.15
     schemes
    0.13
     attempt
    0.13
     orchestr
    0.13
     orchestrated
    0.13
     disguised
    0.13
     wreak
    0.13
     recruiter
    0.13
     hide
    0.12
     lurking
    0.12
    Activations Density 1.693%

    No Known Activations