© 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. 18359
    Prev
    Next
    INDEX
    Explanations

    look like

    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
     [{↵
    -0.09
     Doc
    -0.09
    -find
    -0.09
     Tes
    -0.09
    usses
    -0.09
    /view
    -0.09
    mand
    -0.08
    ĸ
    -0.08
     Semi
    -0.08
     Isle
    -0.08
    POSITIVE LOGITS
     looks
    0.23
    looks
    0.19
     Looks
    0.17
     look
    0.15
     looked
    0.15
     entail
    0.14
     LOOK
    0.14
    Looks
    0.14
     manifests
    0.14
     practically
    0.13
    Activations Density 0.264%

    No Known Activations