© 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. 113293
    Prev
    Next
    INDEX
    Explanations

    barely perceptible

    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
    adh
    -0.10
     SIMPLE
    -0.10
    uga
    -0.09
     relie
    -0.09
     Tou
    -0.09
    oul
    -0.09
    ror
    -0.09
     unab
    -0.09
     straightforward
    -0.09
    axon
    -0.09
    POSITIVE LOGITS
     barely
    0.25
     subtle
    0.24
    bare
    0.18
     subt
    0.18
     hidden
    0.17
     Bare
    0.17
     missed
    0.17
     scarcely
    0.17
     overlooked
    0.16
    blink
    0.15
    Activations Density 0.084%

    No Known Activations