© 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. 54459
    Prev
    Next
    INDEX
    Explanations

    C>T or G>A mutations

    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
     Cann
    -0.09
    rian
    -0.09
    bor
    -0.09
     fresh
    -0.09
     Contractor
    -0.08
     Fresh
    -0.08
     Bul
    -0.08
     resident
    -0.08
    ress
    -0.08
    resh
    -0.08
    POSITIVE LOGITS
    ufs
    0.10
     Gabriel
    0.09
     Mare
    0.08
    shal
    0.08
    /styles
    0.08
     satellite
    0.08
     pij
    0.08
     Lama
    0.08
     aka
    0.08
    chia
    0.08
    Activations Density 0.008%

    No Known Activations