© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 56665
    Prev
    Next
    INDEX
    Explanations

    unsafe behaviors

    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
    fully
    -0.10
    ingly
    -0.10
    ously
    -0.10
    ania
    -0.10
    ry
    -0.09
    alg
    -0.09
    -turned
    -0.09
     arch
    -0.08
    ized
    -0.08
     McKin
    -0.08
    POSITIVE LOGITS
    enti
    0.09
    eph
    0.09
     equival
    0.08
     pec
    0.08
    Dirty
    0.08
    advert
    0.08
    apt
    0.08
     Arte
    0.08
    phen
    0.07
     pencil
    0.07
    Activations Density 0.003%

    No Known Activations