© 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. 3981
    Prev
    Next
    INDEX
    Explanations

    shooting rampage

    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
     signature
    -0.11
     dishonest
    -0.10
     Soph
    -0.09
     vulnerability
    -0.09
     fines
    -0.09
     watermark
    -0.09
     resil
    -0.08
     cheek
    -0.08
     slim
    -0.08
    tol
    -0.08
    POSITIVE LOGITS
     rampage
    0.12
     spree
    0.11
     stalking
    0.10
    /self
    0.09
     justified
    0.09
     serial
    0.09
     euth
    0.09
     rant
    0.09
     zie
    0.09
     untreated
    0.09
    Activations Density 0.173%

    No Known Activations