© 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. 2958
    Prev
    Next
    INDEX
    Explanations

    woman and child depictions

    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
     screen
    -0.09
     Screen
    -0.09
     fluct
    -0.08
     Screening
    -0.08
     screenings
    -0.08
     voice
    -0.08
     sounded
    -0.08
    声
    -0.08
    -screen
    -0.08
     dou
    -0.08
    POSITIVE LOGITS
     posed
    0.14
     poses
    0.13
     pose
    0.13
     Caption
    0.12
    Caption
    0.12
     caption
    0.12
     smiling
    0.11
     seated
    0.11
     subjects
    0.11
     cropped
    0.10
    Activations Density 0.250%

    No Known Activations