© 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. 55174
    Prev
    Next
    INDEX
    Explanations

    surname endings like owski or ovic

    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
    porn
    -0.10
     mist
    -0.10
    ends
    -0.10
     Angry
    -0.10
     Bellev
    -0.10
    Boy
    -0.09
    nik
    -0.09
     Uns
    -0.09
    hton
    -0.09
    wend
    -0.09
    POSITIVE LOGITS
    son
    0.09
     requis
    0.08
    sson
    0.08
    quip
    0.08
    ston
    0.07
    SON
    0.07
     Gow
    0.07
     ~(
    0.07
    "č↵č↵č↵
    0.07
     reliably
    0.07
    Activations Density 0.053%

    No Known Activations