© 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. 116603
    Prev
    Next
    INDEX
    Explanations

    ending punctuation

    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
    wand
    -0.10
     fab
    -0.09
    **↵
    -0.09
     :↵↵↵↵
    -0.09
     Blur
    -0.09
     tether
    -0.09
     snag
    -0.08
     tl
    -0.08
     guarded
    -0.08
    amedi
    -0.08
    POSITIVE LOGITS
    oucher
    0.10
    oux
    0.09
    alli
    0.09
    prite
    0.09
    —in
    0.09
    Narr
    0.09
    iasi
    0.08
    olis
    0.08
     unrestricted
    0.08
     indem
    0.08
    Activations Density 0.013%

    No Known Activations