© 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. 4076
    Prev
    Next
    INDEX
    Explanations

    child abuse or medical conditions

    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
    unt
    -0.10
     siblings
    -0.09
    ilio
    -0.08
     teenager
    -0.08
    ils
    -0.08
    hin
    -0.08
    imates
    -0.08
    uil
    -0.08
     babies
    -0.08
     Howe
    -0.08
    POSITIVE LOGITS
    REN
    0.10
    ishly
    0.09
    reen
    0.09
    cken
    0.09
    hood
    0.09
     prod
    0.09
    abel
    0.08
    ImageSharp
    0.08
    ood
    0.08
    renc
    0.08
    Activations Density 0.087%

    No Known Activations