© 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. 57645
    Prev
    Next
    INDEX
    Explanations

    suicide and related contexts

    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
    IFY
    -0.10
     unh
    -0.10
    iest
    -0.08
    ahan
    -0.08
    ashtra
    -0.08
     Townsend
    -0.08
     Lum
    -0.08
    lier
    -0.08
    859
    -0.08
    ç±
    -0.08
    POSITIVE LOGITS
    .GetBytes
    0.09
    etter
    0.09
     prosper
    0.08
     vig
    0.08
     permalink
    0.08
     ban
    0.08
    irl
    0.08
     Pig
    0.08
     Rubber
    0.08
    SIG
    0.08
    Activations Density 0.008%

    No Known Activations