© 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. 58269
    Prev
    Next
    INDEX
    Explanations

    lehem Records, oliver Young, ology friends

    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
    /assert
    -0.10
    nit
    -0.10
    bos
    -0.09
    uctions
    -0.09
     Bang
    -0.09
    unque
    -0.09
    rail
    -0.09
    §è¡Į
    -0.09
    kehr
    -0.09
    (as
    -0.09
    POSITIVE LOGITS
    iona
    0.08
     dep
    0.08
    olk
    0.07
    aha
    0.07
    orm
    0.07
    agra
    0.07
     Cru
    0.06
     encrypt
    0.06
    eding
    0.06
    iso
    0.06
    Activations Density 0.003%

    No Known Activations