© 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. 5317
    Prev
    Next
    INDEX
    Explanations

    what does ... mean

    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
     be
    -0.14
    Be
    -0.10
    nt
    -0.10
    (be
    -0.10
    mini
    -0.09
    WO
    -0.09
     Morg
    -0.09
    ucas
    -0.09
    bé
    -0.09
     woll
    -0.09
    POSITIVE LOGITS
     mean
    0.18
     differ
    0.18
     consist
    0.17
     belong
    0.15
     imply
    0.15
     entail
    0.14
     represent
    0.14
     depend
    0.14
     resemble
    0.14
     Mean
    0.13
    Activations Density 0.073%

    No Known Activations