© 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. 8205
    Prev
    Next
    INDEX
    Explanations

    population of

    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
     having
    -0.19
    having
    -0.15
     Having
    -0.14
    æľī
    -0.14
    Having
    -0.12
     ayant
    -0.12
     have
    -0.10
    ango
    -0.10
     memiliki
    -0.09
    iless
    -0.09
    POSITIVE LOGITS
     knack
    0.14
     dealings
    0.14
     lined
    0.13
     vedere
    0.13
     recourse
    0.13
    Been
    0.12
     planned
    0.12
     been
    0.12
     underway
    0.12
     handy
    0.12
    Activations Density 1.780%

    No Known Activations