© 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. 28132
    Prev
    Next
    INDEX
    Explanations

    things happening unexpectedly

    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
     permanently
    -0.10
     attraction
    -0.10
     openly
    -0.10
     steadily
    -0.09
    çIJĨ
    -0.09
    azi
    -0.09
    âĨIJ
    -0.09
    hy
    -0.09
     imagin
    -0.09
    adal
    -0.09
    POSITIVE LOGITS
     unsus
    0.14
     suddenly
    0.13
     sudden
    0.11
     unexpectedly
    0.11
     arrival
    0.10
     wake
    0.10
     awake
    0.10
     Suddenly
    0.10
    Suddenly
    0.10
     mid
    0.10
    Activations Density 0.030%

    No Known Activations