© 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. 46852
    Prev
    Next
    INDEX
    Explanations

    predicates /or modify

    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
    iders
    -0.10
    uras
    -0.10
    ask
    -0.09
    eshire
    -0.09
    uster
    -0.09
     Avery
    -0.09
    ulis
    -0.09
     cela
    -0.09
    unte
    -0.09
     Cecil
    -0.09
    POSITIVE LOGITS
     thereof
    0.17
     its
    0.12
    arlo
    0.11
     it
    0.11
    van
    0.10
    دÙĩ
    0.10
     Its
    0.10
    ãģĿãĤĮ
    0.09
     preceded
    0.09
    car
    0.09
    Activations Density 0.897%

    No Known Activations