© 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. 115441
    Prev
    Next
    INDEX
    Explanations

    approach to

    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
     Kendall
    -0.11
     ef
    -0.10
     unm
    -0.09
    ero
    -0.09
     Cyril
    -0.09
    orest
    -0.09
     Wid
    -0.09
     repeal
    -0.09
    eway
    -0.09
    az
    -0.08
    POSITIVE LOGITS
     storytelling
    0.13
     filmm
    0.13
     managing
    0.12
    oco
    0.10
     Daniels
    0.10
     building
    0.10
     оÑĩ
    0.10
    ĥĿ
    0.10
     matchmaking
    0.10
     policym
    0.09
    Activations Density 0.019%

    No Known Activations