© 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. 88115
    Prev
    Next
    INDEX
    Explanations

    oo, oh, oops

    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
    ument
    -0.11
    croft
    -0.09
    nett
    -0.09
    mont
    -0.09
    bower
    -0.09
    wap
    -0.09
    bow
    -0.09
    apis
    -0.09
    ket
    -0.09
    inson
    -0.08
    POSITIVE LOGITS
     oo
    0.14
    oh
    0.14
    oops
    0.12
    ook
    0.11
    oo
    0.11
     OO
    0.10
    Oh
    0.10
    OOK
    0.10
    eh
    0.10
    ops
    0.10
    Activations Density 0.003%

    No Known Activations