© 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. 29782
    Prev
    Next
    INDEX
    Explanations

    ser

    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
     squid
    -0.09
    uye
    -0.09
    isclosed
    -0.09
    xee
    -0.09
    olvency
    -0.09
    Dos
    -0.09
     diss
    -0.09
    izations
    -0.08
    arent
    -0.08
     squares
    -0.08
    POSITIVE LOGITS
    aille
    0.09
    esk
    0.08
     Workspace
    0.08
    (Search
    0.08
     crem
    0.08
    inus
    0.08
    ientes
    0.08
    igenous
    0.08
    Truth
    0.08
    eon
    0.08
    Activations Density 0.131%

    No Known Activations