© 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. 2174
    Prev
    Next
    INDEX
    Explanations

    and then

    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
    aly
    -0.13
     impro
    -0.09
    FTER
    -0.09
    ymm
    -0.08
    aby
    -0.08
     McInt
    -0.08
    cba
    -0.08
     onwards
    -0.08
    otor
    -0.08
     Elliott
    -0.08
    POSITIVE LOGITS
     sticking
    0.12
     stick
    0.10
     adher
    0.10
     sticks
    0.10
     publish
    0.09
    ä¾Ľ
    0.09
     Stick
    0.09
     sell
    0.09
     attach
    0.09
     shove
    0.09
    Activations Density 0.388%

    No Known Activations