© 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. 1449
    Prev
    Next
    INDEX
    Explanations

    harmful, dangerous, adverse, evil

    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
     mover
    -0.09
     Werner
    -0.09
    imos
    -0.09
    quence
    -0.09
     umb
    -0.08
    orr
    -0.08
    acas
    -0.08
    orna
    -0.08
    urge
    -0.08
     unusually
    -0.08
    POSITIVE LOGITS
     inflicted
    0.15
    ous
    0.13
    fully
    0.12
    ously
    0.12
     incurred
    0.11
    ful
    0.11
    uous
    0.11
    /dis
    0.11
    /off
    0.10
    itta
    0.10
    Activations Density 2.229%

    No Known Activations