© 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. 33179
    Prev
    Next
    INDEX
    Explanations

    peculiar, odd, or strange things

    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
     freshly
    -0.10
     pretty
    -0.09
     plenty
    -0.09
     neighb
    -0.09
    agens
    -0.09
    abay
    -0.09
     classic
    -0.09
     standard
    -0.09
    aget
    -0.09
     anyhow
    -0.09
    POSITIVE LOGITS
    -shaped
    0.15
     shaped
    0.14
     sort
    0.13
     mix
    0.13
     mixture
    0.12
    -sort
    0.12
     kind
    0.12
     feeling
    0.12
     hybrid
    0.12
     paradox
    0.12
    Activations Density 0.034%

    No Known Activations