© 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. 29087
    Prev
    Next
    INDEX
    Explanations

    arrogant, arbitrary, haughty

    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
    oyer
    -0.11
    orse
    -0.10
    unta
    -0.10
    s
    -0.10
     uns
    -0.10
     Carpenter
    -0.09
    yo
    -0.09
    Alert
    -0.09
    names
    -0.09
    ìļ´
    -0.09
    POSITIVE LOGITS
    -leaning
    0.10
     enough
    0.09
    uled
    0.09
    /self
    0.09
    /conf
    0.09
     mainland
    0.09
    .gf
    0.08
     strides
    0.08
    achu
    0.08
    /ar
    0.08
    Activations Density 0.007%

    No Known Activations