© 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. 30607
    Prev
    Next
    INDEX
    Explanations

    oh well

    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
     Platt
    -0.09
     Voll
    -0.08
     conduc
    -0.08
     Holder
    -0.08
     YES
    -0.08
     Fetish
    -0.08
    _ins
    -0.08
     unimagin
    -0.08
     Craw
    -0.08
     prow
    -0.08
    POSITIVE LOGITS
     Oops
    0.40
    Oops
    0.34
    oops
    0.30
    ops
    0.20
     darn
    0.17
     mistake
    0.17
     lesson
    0.16
     well
    0.16
     Meh
    0.16
     DERP
    0.15
    Activations Density 0.077%

    No Known Activations