© 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. 15636
    Prev
    Next
    INDEX
    Explanations

    titles followed by names

    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
    peer
    -0.09
    omb
    -0.09
     expans
    -0.09
    amo
    -0.09
    uing
    -0.09
     QT
    -0.08
    endo
    -0.08
    ma
    -0.08
    ched
    -0.08
    Professor
    -0.08
    POSITIVE LOGITS
     rte
    0.10
    ~↵
    0.10
     insn
    0.10
    /Graphics
    0.09
    altar
    0.09
     aire
    0.09
     indeb
    0.09
    iesen
    0.09
     accordion
    0.09
     premise
    0.09
    Activations Density 0.017%

    No Known Activations