© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 31566
    Prev
    Next
    INDEX
    Explanations

    whip up, whipped McCain, whipping boy

    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
     deeply
    -0.11
     Tactics
    -0.10
     Cre
    -0.10
     gran
    -0.09
     Burke
    -0.09
     heavily
    -0.09
     piled
    -0.09
     creeping
    -0.09
    enso
    -0.09
     gra
    -0.09
    POSITIVE LOGITS
     whip
    0.15
     whipped
    0.14
     whipping
    0.14
     around
    0.13
     Around
    0.12
    cord
    0.12
     Whip
    0.12
    around
    0.11
     across
    0.11
     round
    0.10
    Activations Density 0.004%

    No Known Activations