© 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. 14376
    Prev
    Next
    INDEX
    Explanations

    instead of

    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
    &&!
    -0.11
     withhold
    -0.10
     bypass
    -0.10
     Simpson
    -0.10
    ieri
    -0.09
    Exclude
    -0.09
     Honey
    -0.09
    elly
    -0.09
    elor
    -0.09
    PR
    -0.09
    POSITIVE LOGITS
     replaced
    0.25
     Instead
    0.20
    Instead
    0.20
     instead
    0.19
     substituted
    0.17
     favor
    0.16
     focus
    0.16
     favour
    0.15
     replace
    0.15
     replacement
    0.14
    Activations Density 0.423%

    No Known Activations