© 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. 28102
    Prev
    Next
    INDEX
    Explanations

    Dwight, Dworzec, dwelling

    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
     hum
    -0.10
     pleasing
    -0.10
    -transfer
    -0.09
    athon
    -0.08
     ép
    -0.08
     pot
    -0.08
    ORTH
    -0.08
    Bon
    -0.08
     Bon
    -0.08
     Orange
    -0.07
    POSITIVE LOGITS
    ija
    0.14
     dw
    0.13
     Dw
    0.13
    amil
    0.12
    ipay
    0.11
    edit
    0.11
     dwelling
    0.11
     dwell
    0.11
    indle
    0.11
    allah
    0.11
    Activations Density 0.034%

    No Known Activations