© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 90003
    Prev
    Next
    INDEX
    Explanations

    names starting with E, P, L, V, M, I, C, F

    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
     damned
    -0.09
    -turned
    -0.09
     damn
    -0.09
     measure
    -0.09
    SKU
    -0.09
    castle
    -0.08
    acin
    -0.08
     measures
    -0.08
    esso
    -0.08
    inct
    -0.08
    POSITIVE LOGITS
    lopen
    0.09
    [url
    0.09
     Ged
    0.09
    âĢij
    0.09
    cep
    0.08
     Wilkinson
    0.08
     Pratt
    0.08
     Caul
    0.08
     womens
    0.08
    ibu
    0.08
    Activations Density 0.007%

    No Known Activations