© 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. 33127
    Prev
    Next
    INDEX
    Explanations

    Jake Owen, Danny Glover

    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
    ãĤ£
    -0.13
    fully
    -0.12
    ingly
    -0.11
    nable
    -0.10
    lock
    -0.10
     unp
    -0.10
    ilton
    -0.09
    onia
    -0.09
    ned
    -0.09
    shire
    -0.09
    POSITIVE LOGITS
    inx
    0.09
    emin
    0.09
    ../../
    0.08
    .YesNo
    0.08
    illum
    0.08
    etty
    0.08
     sail
    0.07
    alth
    0.07
    veau
    0.07
    asel
    0.07
    Activations Density 0.319%

    No Known Activations