© 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. 57849
    Prev
    Next
    INDEX
    Explanations

    murder and violent crimes

    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
     touched
    -0.09
     getBy
    -0.09
    ç¦
    -0.09
    ated
    -0.08
    -0.08
     Chr
    -0.08
     Orr
    -0.08
    Cases
    -0.08
    czy
    -0.08
    acer
    -0.08
    POSITIVE LOGITS
    ron
    0.09
    mens
    0.09
     soft
    0.08
    rena
    0.08
     natural
    0.08
    ooth
    0.08
     Hidden
    0.08
     infect
    0.08
    upp
    0.08
     Natural
    0.07
    Activations Density 0.004%

    No Known Activations