© 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. 88170
    Prev
    Next
    INDEX
    Explanations

    starring roles

    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
     Qual
    -0.10
     workings
    -0.10
     rendez
    -0.10
    iez
    -0.10
     Sta
    -0.10
     Contest
    -0.10
    497
    -0.10
     Elo
    -0.10
     bund
    -0.10
    &m
    -0.10
    POSITIVE LOGITS
     alongside
    0.14
     own
    0.11
    /support
    0.11
     starring
    0.10
     upcoming
    0.09
     movies
    0.09
     alone
    0.09
    /co
    0.09
     Own
    0.08
     propio
    0.08
    Activations Density 0.081%

    No Known Activations