© 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. 3684
    Prev
    Next
    INDEX
    Explanations

    ending or stopping

    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
    hic
    -0.09
    endon
    -0.09
     dec
    -0.09
    edium
    -0.08
    avin
    -0.08
    cant
    -0.08
     unwilling
    -0.08
     mold
    -0.08
     Mama
    -0.08
     vacant
    -0.08
    POSITIVE LOGITS
    Live
    0.10
     circulated
    0.10
    IGIN
    0.09
    uf
    0.09
     immediately
    0.09
    OE
    0.08
    egr
    0.08
     spre
    0.08
     penetr
    0.08
    oe
    0.08
    Activations Density 0.137%

    No Known Activations