© 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. 17524
    Prev
    Next
    INDEX
    Explanations

    pollard or polls or polluted

    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
    esta
    -0.10
     uns
    -0.09
    lier
    -0.09
    ially
    -0.09
    heel
    -0.09
    lc
    -0.09
    anova
    -0.08
     amusing
    -0.08
     Fitzgerald
    -0.08
    appa
    -0.08
    POSITIVE LOGITS
     poll
    0.20
     Poll
    0.20
     polls
    0.17
     polling
    0.16
    ination
    0.15
    poll
    0.15
    Poll
    0.14
    uted
    0.14
    ution
    0.14
    uting
    0.14
    Activations Density 0.032%

    No Known Activations