© 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-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 88259
    Prev
    Next
    INDEX
    Explanations

    abbreviations or initial parts of words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åł
    -0.10
    .`
    -0.10
    asion
    -0.10
    č
    -0.10
     dó
    -0.10
    ::*;↵
    -0.10
     Marin
    -0.10
    unto
    -0.10
    hem
    -0.10
    volatile
    -0.09
    POSITIVE LOGITS
     Scre
    0.08
    {EIF
    0.07
    antino
    0.07
    Statics
    0.07
    CCI
    0.07
     clums
    0.07
    abbo
    0.06
     precis
    0.06
    chwitz
    0.06
    IMS
    0.06
    Activations Density 1.358%

    No Known Activations