© 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. 54845
    Prev
    Next
    INDEX
    Explanations

    places and locations

    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
    pan
    -0.08
    orre
    -0.06
    kees
    -0.06
     capitals
    -0.06
     Dy
    -0.06
    counts
    -0.05
     W
    -0.05
    posit
    -0.05
     Laurent
    -0.05
     Gift
    -0.05
    POSITIVE LOGITS
    isel
    0.10
    ikon
    0.10
     briefly
    0.10
    (slice
    0.10
    bounding
    0.10
    .mem
    0.10
    ÅĤug
    0.10
    invisible
    0.10
     Pant
    0.10
    zb
    0.10
    Activations Density 0.046%

    No Known Activations