© 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. 91260
    Prev
    Next
    INDEX
    Explanations

    Japanese personal names

    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
     Twins
    -0.08
     Hope
    -0.08
     vant
    -0.08
     Aurora
    -0.08
     Sacred
    -0.08
     Rafael
    -0.08
     glacier
    -0.08
    rah
    -0.08
     dealloc
    -0.08
     Adrian
    -0.08
    POSITIVE LOGITS
    è´
    0.10
    nces
    0.10
     dick
    0.09
     solidity
    0.09
     contrace
    0.09
    midd
    0.09
    ldr
    0.09
    itung
    0.09
     milit
    0.09
    slack
    0.09
    Activations Density 0.303%

    No Known Activations