© 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. 57052
    Prev
    Next
    INDEX
    Explanations

    deduced words

    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
    aux
    -0.10
    rier
    -0.09
    ices
    -0.09
    úb
    -0.09
    ances
    -0.09
    marshall
    -0.09
     esk
    -0.09
    åı¸
    -0.09
    cies
    -0.09
    anta
    -0.09
    POSITIVE LOGITS
    ively
    0.13
    oose
    0.10
     Ded
    0.09
    æk
    0.09
     Kare
    0.09
     Andrews
    0.08
    ived
    0.08
    ed
    0.08
    usch
    0.08
    iu
    0.08
    Activations Density 0.002%

    No Known Activations