© 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. 114959
    Prev
    Next
    INDEX
    Explanations

    description of conditions and events

    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
     likewise
    -0.12
     similarly
    -0.10
     ours
    -0.09
     bust
    -0.09
     we
    -0.09
    ollo
    -0.09
    Similarly
    -0.08
     campuses
    -0.08
     ebenfalls
    -0.08
     onboard
    -0.08
    POSITIVE LOGITS
    /cms
    0.10
    582
    0.09
     Kb
    0.09
    uppy
    0.09
    .dc
    0.09
    lix
    0.09
    UNT
    0.08
     autob
    0.08
    lav
    0.08
     Kay
    0.08
    Activations Density 0.216%

    No Known Activations