© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 7823
    Prev
    Next
    INDEX
    Explanations

    average, normal, intermediate

    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
     extreme
    -0.10
     unusually
    -0.10
    .rar
    -0.10
    bib
    -0.10
     tarde
    -0.09
     Dah
    -0.09
     Extreme
    -0.09
     bib
    -0.09
    942
    -0.09
     unusual
    -0.09
    POSITIVE LOGITS
     sized
    0.23
    -sized
    0.21
     Sized
    0.16
    -size
    0.15
     size
    0.14
    /mod
    0.12
     attractiveness
    0.11
    size
    0.11
     priced
    0.11
    大å°ı
    0.11
    Activations Density 0.139%

    No Known Activations