© 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. 32256
    Prev
    Next
    INDEX
    Explanations

    What's wrong with

    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
    abi
    -0.11
    rys
    -0.10
    cing
    -0.09
    nam
    -0.09
    isting
    -0.09
     Mang
    -0.09
    /link
    -0.09
     whitelist
    -0.09
     mang
    -0.09
    /fire
    -0.09
    POSITIVE LOGITS
     relying
    0.11
     bes
    0.09
     using
    0.09
    edly
    0.09
    Dod
    0.09
     deferred
    0.08
     having
    0.08
     me
    0.08
     incest
    0.08
     duplic
    0.08
    Activations Density 0.025%

    No Known Activations