© 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. 18735
    Prev
    Next
    INDEX
    Explanations

    hyphenated codes with numbers/letters

    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
     struct
    -0.10
    >/
    -0.10
     interchangeable
    -0.09
    zp
    -0.09
     Ney
    -0.09
     Tweet
    -0.09
     transplant
    -0.09
     setter
    -0.09
     reportedly
    -0.08
    qq
    -0.08
    POSITIVE LOGITS
     enthus
    0.09
    -TV
    0.09
     acronym
    0.08
     Rak
    0.08
    004
    0.08
     Lamar
    0.08
     Centro
    0.08
    adal
    0.08
    ####↵
    0.08
     teh
    0.08
    Activations Density 0.225%

    No Known Activations