© 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. 28272
    Prev
    Next
    INDEX
    Explanations

    Boo, Boh, and related sounds

    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
     cheap
    -0.11
     minute
    -0.09
    mes
    -0.09
    reten
    -0.09
    enso
    -0.09
     juxtap
    -0.09
    apore
    -0.09
    -Un
    -0.09
     Cheap
    -0.09
    bian
    -0.09
    POSITIVE LOGITS
    Bo
    0.13
     bo
    0.13
     Bo
    0.12
     Boh
    0.12
     Boo
    0.11
    obo
    0.11
    -bo
    0.11
     Boeh
    0.10
    ogie
    0.10
    strap
    0.10
    Activations Density 0.089%

    No Known Activations