© 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. 858
    Prev
    Next
    INDEX
    Explanations

    analytics insights narratives

    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
    iate
    -0.12
    liness
    -0.12
    ROUP
    -0.11
    lies
    -0.10
    bery
    -0.10
    iates
    -0.10
    ÑģÑĤв
    -0.10
    stown
    -0.10
    overe
    -0.10
    ç±
    -0.10
    POSITIVE LOGITS
    ions
    0.10
    ron
    0.10
    ors
    0.09
    ilion
    0.09
    ppy
    0.08
    ãĥ£
    0.08
    ibly
    0.08
    ure
    0.08
    gos
    0.08
    	namespace
    0.08
    Activations Density 5.355%

    No Known Activations