© 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. 57461
    Prev
    Next
    INDEX
    Explanations

    comment / Re:

    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
     tir
    -0.11
    [".
    -0.11
     gio
    -0.10
    baum
    -0.10
     Weber
    -0.10
     Adler
    -0.10
    itzer
    -0.10
    )))),
    -0.10
    ÂŃing
    -0.10
    ibox
    -0.09
    POSITIVE LOGITS
     Hum
    0.09
     arresting
    0.08
     arrests
    0.07
    erto
    0.07
    Hum
    0.07
     lasting
    0.07
    etros
    0.07
     den
    0.07
     hum
    0.07
    etro
    0.07
    Activations Density 0.001%

    No Known Activations