© 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. 26786
    Prev
    Next
    INDEX
    Explanations

    discussion about

    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
     goodbye
    -0.10
    ufen
    -0.09
     myself
    -0.09
     sut
    -0.09
     loos
    -0.09
    ivre
    -0.09
     slides
    -0.08
     Russo
    -0.08
    andid
    -0.08
     himself
    -0.08
    POSITIVE LOGITS
     explicitly
    0.11
    ses
    0.10
    /show
    0.10
    zens
    0.10
    618
    0.09
    jan
    0.09
     expressly
    0.09
    /support
    0.09
     describes
    0.09
     briefly
    0.09
    Activations Density 0.660%

    No Known Activations