© 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. 25891
    Prev
    Next
    INDEX
    Explanations

    voting process ballots

    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
     sno
    -0.10
    amer
    -0.10
     brainstorm
    -0.10
     carrier
    -0.09
    iert
    -0.09
     searched
    -0.09
    -cut
    -0.09
    ulia
    -0.09
     unpl
    -0.09
     capture
    -0.09
    POSITIVE LOGITS
     voting
    0.33
     Voting
    0.30
     votes
    0.28
     vote
    0.28
    Vote
    0.25
    vote
    0.24
     Vote
    0.23
     voter
    0.23
     voters
    0.23
     vot
    0.22
    Activations Density 0.127%

    No Known Activations