© 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. 57316
    Prev
    Next
    INDEX
    Explanations

    numerical sequence formatting

    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
    asd
    -0.09
     qualification
    -0.09
    Ordered
    -0.08
    (er
    -0.08
    anny
    -0.08
     Rim
    -0.08
    ticks
    -0.08
     Roose
    -0.08
    çĽ
    -0.08
    )L
    -0.08
    POSITIVE LOGITS
    inet
    0.10
    acin
    0.09
    lg
    0.09
     HuffPost
    0.08
     herr
    0.08
     Wah
    0.08
     *);↵↵
    0.08
    GF
    0.08
     dash
    0.08
    avar
    0.08
    Activations Density 0.008%

    No Known Activations