© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 27910
    Prev
    Next
    INDEX
    Explanations

    go again, is the, disingenuous, swear we, create menu

    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
     shit
    -0.11
     Bingo
    -0.10
     ugly
    -0.10
    Looks
    -0.10
     bingo
    -0.10
     upset
    -0.10
     unpopular
    -0.10
     Looks
    -0.10
     Daddy
    -0.10
     cosa
    -0.09
    POSITIVE LOGITS
     incor
    0.13
     sometimes
    0.11
     brib
    0.10
     someday
    0.10
    dale
    0.09
     unbelievable
    0.09
    ofi
    0.09
     priceless
    0.09
     perv
    0.09
     hopeless
    0.08
    Activations Density 0.042%

    No Known Activations