© 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. 595
    Prev
    Next
    INDEX
    Explanations

    photomask, alignment mark, backlight, transformer, endoscopic operation, GBT, recognition, impact, rough hole

    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
    Âł
    -0.11
    âĢ¦
    -0.08
     eventual
    -0.08
    hz
    -0.08
    —and
    -0.08
     now
    -0.08
     courtesy
    -0.08
     âĢ¦
    -0.08
     ÂŃ
    -0.07
     caveat
    -0.07
    POSITIVE LOGITS
     oneself
    0.14
     equipments
    0.13
     thereof
    0.13
    !!)↵
    0.12
    0.11
    cil
    0.11
    Cls
    0.11
    .so
    0.11
    âij
    0.11
    unan
    0.11
    Activations Density 1.460%

    No Known Activations