© 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. 5863
    Prev
    Next
    INDEX
    Explanations

    full, large, small, numbers and units

    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
     ê
    -0.09
     Pik
    -0.09
     Peb
    -0.09
    -extra
    -0.09
    abras
    -0.09
     Kurt
    -0.09
     Tits
    -0.08
     fiz
    -0.08
     xt
    -0.08
    aggio
    -0.08
    POSITIVE LOGITS
     full
    0.23
     outright
    0.21
    /full
    0.19
    (full
    0.17
     Full
    0.17
    full
    0.16
    Full
    0.16
     substantive
    0.15
     larger
    0.15
     FULL
    0.14
    Activations Density 0.759%

    No Known Activations