© 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. 30660
    Prev
    Next
    INDEX
    Explanations

    plenty 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
    zik
    -0.11
     Ree
    -0.09
    ع
    -0.08
     squeeze
    -0.08
     upfront
    -0.08
     noop
    -0.08
     Few
    -0.08
     pendant
    -0.08
    ار
    -0.08
     occasionally
    -0.07
    POSITIVE LOGITS
     plenty
    0.21
     Plenty
    0.18
     plentiful
    0.17
    replacement
    0.13
     inex
    0.13
     ample
    0.13
     replacement
    0.12
     fish
    0.12
     abundance
    0.11
     thousands
    0.11
    Activations Density 0.035%

    No Known Activations