© 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. 8035
    Prev
    Next
    INDEX
    Explanations

    much of the

    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
    Not in Any Lists

    No Comments

    Negative Logits
     strictly
    -0.08
    ief
    -0.08
    bit
    -0.08
     stars
    -0.08
    tri
    -0.08
    IDA
    -0.08
     Freak
    -0.07
    ence
    -0.07
     vox
    -0.07
     ass
    -0.07
    POSITIVE LOGITS
    ajs
    0.12
    ilan
    0.10
     semantics
    0.10
     equipments
    0.10
    ress
    0.10
    ockey
    0.10
     depends
    0.10
    ael
    0.09
    icts
    0.09
     infancy
    0.09
    Activations Density 0.103%

    No Known Activations