© 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. 55350
    Prev
    Next
    INDEX
    Explanations

    continues or goes on to

    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
     Wahl
    -0.07
     Ack
    -0.07
     BRO
    -0.06
    ouser
    -0.06
    iar
    -0.06
    åĬ¨çĶŁæĪIJ
    -0.06
     flashlight
    -0.06
    ip
    -0.06
    draw
    -0.06
    -e
    -0.06
    POSITIVE LOGITS
    cob
    0.11
    bay
    0.11
    iffe
    0.10
    .getElementsByName
    0.10
    ologi
    0.10
     dann
    0.10
     szer
    0.10
     Olympia
    0.10
    attach
    0.09
    uario
    0.09
    Activations Density 0.009%

    No Known Activations