© 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. 49303
    Prev
    Next
    INDEX
    Explanations

    free or available

    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
     DVDs
    -0.17
     dvd
    -0.15
     DVD
    -0.15
    DVD
    -0.13
     CDs
    -0.12
     produk
    -0.12
     books
    -0.11
     Produk
    -0.11
     moth
    -0.10
     mounting
    -0.10
    POSITIVE LOGITS
     Kindle
    0.15
     Amazon
    0.11
    Kind
    0.09
     experiment
    0.09
    estar
    0.09
     Experiment
    0.08
     blind
    0.08
     ere
    0.08
     inflate
    0.08
     epis
    0.08
    Activations Density 0.142%

    No Known Activations