© 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. 8520
    Prev
    Next
    INDEX
    Explanations

    words like only, less, other, itself, second, repeated, exclusive, -free, free

    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
    auer
    -0.07
    ÑĢан
    -0.06
     ent
    -0.06
     FAR
    -0.06
     Curt
    -0.06
     Mail
    -0.06
     elbows
    -0.06
     Moses
    -0.06
     Milk
    -0.06
     Grant
    -0.05
    POSITIVE LOGITS
    rvine
    0.12
    utter
    0.12
    PRS
    0.12
    ¡°
    0.12
     Luz
    0.11
     Ney
    0.11
    prs
    0.11
    LAG
    0.11
    lbrace
    0.10
    ashboard
    0.10
    Activations Density 1.008%

    No Known Activations