© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 111413
    Prev
    Next
    INDEX
    Explanations

    DO NOT ALTER OR REMOVE COPYRIGHT NO

    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
    Negative Logits
     zar
    -0.10
    ULK
    -0.09
     libero
    -0.09
     hijo
    -0.09
     kino
    -0.09
    "s
    -0.09
    ecz
    -0.09
    -share
    -0.08
    -sama
    -0.08
     Inbox
    -0.08
    POSITIVE LOGITS
    eph
    0.09
     Sawyer
    0.08
     Sue
    0.08
     Bust
    0.08
     Suk
    0.08
     Hairst
    0.08
     Dial
    0.07
     Slater
    0.07
     nails
    0.07
     Orch
    0.07
    Activations Density 0.001%

    No Known Activations