© 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. 25234
    Prev
    Next
    INDEX
    Explanations

    explaining problems

    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
    iges
    -0.10
    Such
    -0.10
    AsString
    -0.10
     Such
    -0.10
     such
    -0.10
     Speedway
    -0.09
     agreement
    -0.09
     Fortune
    -0.09
    XS
    -0.09
     happily
    -0.09
    POSITIVE LOGITS
     theres
    0.18
     didnt
    0.14
     everytime
    0.14
     wont
    0.13
     youre
    0.13
     cant
    0.13
     doesnt
    0.12
     isnt
    0.12
    nt
    0.11
     Majority
    0.11
    Activations Density 0.205%

    No Known Activations