© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 50707
    Prev
    Next
    INDEX
    Explanations

    at all times

    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
    abil
    -0.08
    rogen
    -0.07
    urs
    -0.07
    rog
    -0.07
     Bowman
    -0.07
     Minute
    -0.07
     Stra
    -0.07
    afs
    -0.07
    ICC
    -0.06
     Sovere
    -0.06
    POSITIVE LOGITS
     times
    0.21
     corners
    0.16
     ages
    0.15
    times
    0.14
     levels
    0.13
     points
    0.13
     stages
    0.13
    levels
    0.12
     corner
    0.12
     costs
    0.12
    Activations Density 0.039%

    No Known Activations