© 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. 116186
    Prev
    Next
    INDEX
    Explanations

    automatically for

    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
    elas
    -0.11
    har
    -0.11
    861
    -0.10
     Morm
    -0.10
    jin
    -0.10
    +self
    -0.10
    ubre
    -0.10
    rais
    -0.10
    ibri
    -0.10
    .self
    -0.09
    POSITIVE LOGITS
     behalf
    0.41
     stead
    0.17
     for
    0.17
     automatically
    0.15
     bagi
    0.15
    代
    0.15
    for
    0.14
     FOR
    0.13
     длÑı
    0.13
    	for
    0.13
    Activations Density 0.590%

    No Known Activations