© 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. 49529
    Prev
    Next
    INDEX
    Explanations

    request or propose

    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
    -aff
    -0.10
     Slater
    -0.10
     ber
    -0.10
     nons
    -0.09
    wel
    -0.09
    imals
    -0.09
    RTL
    -0.09
     blah
    -0.09
     subur
    -0.09
     lash
    -0.09
    POSITIVE LOGITS
     request
    0.14
     Requests
    0.12
     proposed
    0.12
     requester
    0.12
     requests
    0.12
     suggestion
    0.11
     pleading
    0.11
     persistence
    0.11
    request
    0.11
    -request
    0.10
    Activations Density 0.007%

    No Known Activations