© 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. 49257
    Prev
    Next
    INDEX
    Explanations

    some alternatives

    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
     people
    -0.12
     peoples
    -0.10
    people
    -0.08
     flatt
    -0.08
     millions
    -0.08
     recipients
    -0.08
     sufferers
    -0.08
     individuals
    -0.08
     victims
    -0.08
     Neither
    -0.07
    POSITIVE LOGITS
    Some
    0.15
     Some
    0.14
     some
    0.14
     beware
    0.13
    erer
    0.13
    some
    0.13
     niche
    0.12
     ours
    0.12
    _some
    0.12
    Prices
    0.12
    Activations Density 0.127%

    No Known Activations