© 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. 49525
    Prev
    Next
    INDEX
    Explanations

    discussion of related art

    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
     discussions
    -0.12
    ropp
    -0.11
     explanations
    -0.11
     explanation
    -0.11
     descriptions
    -0.11
    Descriptions
    -0.10
    Explanation
    -0.10
     retract
    -0.10
     tight
    -0.10
    DESCRIPTION
    -0.10
    POSITIVE LOGITS
     openly
    0.23
     briefly
    0.16
     thoroughly
    0.15
     extensively
    0.14
     candid
    0.14
     endlessly
    0.14
     merits
    0.13
     freely
    0.13
     aloud
    0.12
     topic
    0.12
    Activations Density 0.239%

    No Known Activations