© 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. 58079
    Prev
    Next
    INDEX
    Explanations

    ravages, ravine, Raven

    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
    logue
    -0.09
    pector
    -0.09
    nik
    -0.09
     Hyp
    -0.08
     Werk
    -0.08
    ocio
    -0.08
    aro
    -0.08
    ardon
    -0.08
    nick
    -0.08
    ocket
    -0.08
    POSITIVE LOGITS
    hill
    0.10
    ining
    0.09
    fal
    0.09
    mentor
    0.08
    inner
    0.08
    bau
    0.08
    aged
    0.08
     strands
    0.08
    áŀ¶
    0.08
    earn
    0.08
    Activations Density 0.002%

    No Known Activations