© 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. 88690
    Prev
    Next
    INDEX
    Explanations

    out of the bottle, tip of the iceberg, foxhole

    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
     runnable
    -0.11
    zza
    -0.11
    iquid
    -0.11
    Gallery
    -0.11
     spare
    -0.10
    clare
    -0.10
     karma
    -0.10
     swo
    -0.10
    XS
    -0.10
     voucher
    -0.10
    POSITIVE LOGITS
     genie
    0.27
     Pandora
    0.25
     proverb
    0.21
     iceberg
    0.21
     cat
    0.21
     elephant
    0.20
     camel
    0.20
     horse
    0.18
    cat
    0.16
     Cat
    0.16
    Activations Density 0.123%

    No Known Activations