© 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. 7353
    Prev
    Next
    INDEX
    Explanations

    unplanned occurrences or 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
     Acres
    -0.08
    ichi
    -0.08
    /vnd
    -0.08
     confidently
    -0.08
     Quint
    -0.08
     meas
    -0.07
    bart
    -0.07
     GAR
    -0.07
     Garrett
    -0.07
     reset
    -0.07
    POSITIVE LOGITS
     accidental
    0.37
     unintention
    0.33
     accidentally
    0.33
     spontaneous
    0.31
     unintended
    0.30
     inadvert
    0.30
     unpl
    0.30
     spontaneously
    0.30
     incidental
    0.28
     inadvertently
    0.27
    Activations Density 0.288%

    No Known Activations