© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 89941
    Prev
    Next
    INDEX
    Explanations

    soap opera and APIs

    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
    urations
    -0.10
    iap
    -0.10
    hoot
    -0.10
    ned
    -0.09
    nable
    -0.09
    uffer
    -0.09
    aur
    -0.08
    elog
    -0.08
    aec
    -0.08
     gar
    -0.08
    POSITIVE LOGITS
     opera
    0.18
     Opera
    0.14
     oper
    0.12
    Opera
    0.12
    iness
    0.11
    stone
    0.11
    ify
    0.10
    uds
    0.10
    ateria
    0.10
    wort
    0.10
    Activations Density 0.011%

    No Known Activations