© 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. 88644
    Prev
    Next
    INDEX
    Explanations

    Chinese names and initials

    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
    thr
    -0.09
    cae
    -0.09
    OTT
    -0.09
    inne
    -0.09
    CN
    -0.09
    -register
    -0.09
     fertile
    -0.09
    hani
    -0.08
    antha
    -0.08
    NH
    -0.08
    POSITIVE LOGITS
    µ¬
    0.10
     unp
    0.10
    upo
    0.10
    stants
    0.10
    ians
    0.09
    uppy
    0.09
     famil
    0.09
    tings
    0.09
     unpl
    0.08
    amage
    0.08
    Activations Density 0.029%

    No Known Activations