© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 90227
    Prev
    Next
    INDEX
    Explanations

    axis and invention relates

    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
     Emm
    -0.11
     Beng
    -0.09
     sexually
    -0.09
    yor
    -0.09
    aux
    -0.09
    institution
    -0.09
    اÛĮ
    -0.09
    inus
    -0.09
    __':↵
    -0.09
    erek
    -0.09
    POSITIVE LOGITS
    urette
    0.10
     paren
    0.10
    idue
    0.09
     Packages
    0.09
     Mut
    0.08
     quo
    0.08
    agher
    0.08
    bek
    0.08
     Qing
    0.08
     mund
    0.08
    Activations Density 0.002%

    No Known Activations