© 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. 28858
    Prev
    Next
    INDEX
    Explanations

    has proven / resulted / generated / changed / enabled / made / allowed

    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
     Expires
    -0.09
    ipop
    -0.09
    mlink
    -0.09
    dden
    -0.09
     recurs
    -0.09
     bath
    -0.08
     Freak
    -0.08
     sel
    -0.08
     cling
    -0.08
     healed
    -0.08
    POSITIVE LOGITS
     revolution
    0.36
     Revolution
    0.27
     usher
    0.26
    revolution
    0.25
     revolutionary
    0.23
     enabling
    0.22
     democrat
    0.21
     enable
    0.21
     enables
    0.21
     revolutions
    0.20
    Activations Density 1.093%

    No Known Activations