© 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. 58557
    Prev
    Next
    INDEX
    Explanations

    return or happen

    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
     Kak
    -0.10
     wegen
    -0.10
    ugin
    -0.09
    _-_
    -0.08
    dig
    -0.08
     Spiel
    -0.08
    /design
    -0.08
    uhan
    -0.08
    =cut
    -0.08
     forfe
    -0.08
    POSITIVE LOGITS
    è¿ĶåĽŀ
    0.10
     silently
    0.09
     harmless
    0.09
    emy
    0.09
     Cruise
    0.09
     output
    0.09
     tamp
    0.08
     è¿ĶåĽŀ
    0.08
     silent
    0.08
     strtoupper
    0.08
    Activations Density 0.038%

    No Known Activations