© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 1250
    Prev
    Next
    INDEX
    Explanations

    holder / container / item

    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
     canned
    -0.12
    kontakte
    -0.11
     wrinkles
    -0.11
    uite
    -0.11
    ROID
    -0.10
     bottled
    -0.10
     excer
    -0.10
    STAR
    -0.10
     quoted
    -0.10
     tej
    -0.10
    POSITIVE LOGITS
    -shaped
    0.13
    -sized
    0.12
     holder
    0.11
    /table
    0.10
    /button
    0.10
    /window
    0.10
     belonging
    0.09
     handy
    0.09
     sized
    0.09
    /card
    0.09
    Activations Density 2.288%

    No Known Activations