© 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. 17829
    Prev
    Next
    INDEX
    Explanations

    MIT license

    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
    agos
    -0.10
    scri
    -0.10
    adir
    -0.09
    cht
    -0.09
    {"
    -0.09
    aret
    -0.09
    wiki
    -0.09
     Loft
    -0.09
     Scri
    -0.09
    ãģ°
    -0.09
    POSITIVE LOGITS
     tightly
    0.17
     tighter
    0.15
    opo
    0.12
    -ball
    0.11
     tight
    0.11
    ertino
    0.10
     firmly
    0.10
     halo
    0.10
     balls
    0.10
     awkward
    0.09
    Activations Density 0.003%

    No Known Activations