© 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. 29777
    Prev
    Next
    INDEX
    Explanations

    official edition stadium coin

    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
     unsuccessfully
    -0.09
     roundup
    -0.09
     assorted
    -0.08
    .ru
    -0.08
    ì¶
    -0.08
     checklist
    -0.08
    âĢº
    -0.08
    :c
    -0.08
     Chim
    -0.08
     uncon
    -0.07
    POSITIVE LOGITS
     HD
    0.10
     incl
    0.10
    ĵį
    0.10
     legitim
    0.09
    idal
    0.09
    927
    0.09
     English
    0.09
    Explicit
    0.09
     sponsorship
    0.09
     HQ
    0.09
    Activations Density 0.039%

    No Known Activations