© 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. 117325
    Prev
    Next
    INDEX
    Explanations

    cl, clib, clue, cloning, clusters

    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
    aken
    -0.09
     enduring
    -0.09
    abet
    -0.08
    idd
    -0.08
    edy
    -0.08
    utor
    -0.08
    uit
    -0.08
    eth
    -0.07
     Stan
    -0.07
    nable
    -0.07
    POSITIVE LOGITS
    /cl
    0.17
     clue
    0.16
    -cl
    0.16
     Cl
    0.16
     clutch
    0.16
     clues
    0.16
     clap
    0.15
     Clayton
    0.15
     clustering
    0.15
     cliffs
    0.15
    Activations Density 0.033%

    No Known Activations