© 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. 111418
    Prev
    Next
    INDEX
    Explanations

    work in progress

    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
    Negative Logits
     eup
    -0.11
    Enlarge
    -0.10
    /Peak
    -0.10
    ewe
    -0.10
     coerc
    -0.10
     nostalg
    -0.10
    veh
    -0.09
    Redirect
    -0.09
    моÑĤ
    -0.09
     Retro
    -0.09
    POSITIVE LOGITS
     unfinished
    0.72
    unfinished
    0.54
     incomplete
    0.53
    Incomplete
    0.37
     provisional
    0.34
     draft
    0.34
     immature
    0.31
     interim
    0.31
     preliminary
    0.31
     finished
    0.31
    Activations Density 1.949%

    No Known Activations