© 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. 26417
    Prev
    Next
    INDEX
    Explanations

    instead, unintended outcomes

    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
     Bever
    -0.10
     Doll
    -0.09
    reuse
    -0.09
     Alvarez
    -0.09
     fend
    -0.08
    ture
    -0.08
     sucker
    -0.08
    714
    -0.08
    apot
    -0.08
    CB
    -0.08
    POSITIVE LOGITS
     instead
    0.37
     Instead
    0.32
    instead
    0.30
    Instead
    0.29
     unintended
    0.22
     inadvertently
    0.21
     unintention
    0.21
     ended
    0.20
     result
    0.17
     ends
    0.16
    Activations Density 0.182%

    No Known Activations