© 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. 57494
    Prev
    Next
    INDEX
    Explanations

    study of

    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
    tog
    -0.10
    yms
    -0.10
    ross
    -0.10
    ::{↵
    -0.10
    ssc
    -0.10
    sa
    -0.09
     sul
    -0.09
    ĴĮ
    -0.09
    |array
    -0.09
     segu
    -0.09
    POSITIVE LOGITS
    UD
    0.08
    fox
    0.07
    rei
    0.07
    ilit
    0.07
    DN
    0.07
    еÑģÑĤи
    0.07
    ause
    0.07
    ptr
    0.07
    dn
    0.07
    auses
    0.07
    Activations Density 0.001%

    No Known Activations