© 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. 89479
    Prev
    Next
    INDEX
    Explanations

    bizarre shocking or hilarious

    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
     selfish
    -0.15
     smarty
    -0.13
     fuss
    -0.13
     inconvenient
    -0.12
     fancy
    -0.11
     impatient
    -0.11
     pes
    -0.11
     prec
    -0.11
     gossip
    -0.11
     tricky
    -0.11
    POSITIVE LOGITS
     WTF
    0.19
     hilar
    0.19
     bizarre
    0.16
     hilarious
    0.16
     unintention
    0.16
     baff
    0.15
     MST
    0.15
     horrifying
    0.15
     insanity
    0.15
     surreal
    0.15
    Activations Density 0.406%

    No Known Activations