© 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. 46766
    Prev
    Next
    INDEX
    Explanations

    paragraph break

    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
     “âĢ¦
    -0.13
     Sorry
    -0.11
     sorry
    -0.11
     “[
    -0.11
    “That
    -0.11
     Bah
    -0.10
    LY
    -0.10
     “
    -0.10
    cff
    -0.10
    Sy
    -0.10
    POSITIVE LOGITS
    Eventually
    0.10
     prov
    0.09
    lix
    0.09
    Originally
    0.08
    ather
    0.08
    Initially
    0.08
     veter
    0.08
     Orchard
    0.08
     prefetch
    0.08
    oon
    0.07
    Activations Density 0.042%

    No Known Activations