© 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. 47803
    Prev
    Next
    INDEX
    Explanations

    who prefer or want

    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
     Lehr
    -0.09
     traj
    -0.09
    Restart
    -0.09
     behaved
    -0.09
     aboard
    -0.09
     costing
    -0.08
     incent
    -0.08
    ebin
    -0.08
     Ran
    -0.08
     remarkably
    -0.08
    POSITIVE LOGITS
     want
    0.17
     appreciate
    0.16
     prefer
    0.15
    want
    0.14
     enjoy
    0.14
     wants
    0.13
     wish
    0.13
     enjoys
    0.13
     prefers
    0.13
     wondered
    0.12
    Activations Density 0.038%

    No Known Activations