© 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. 26813
    Prev
    Next
    INDEX
    Explanations

    academic references like et al

    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
     facet
    -0.10
     laden
    -0.08
    airo
    -0.08
     facets
    -0.08
     capit
    -0.08
     ostensibly
    -0.08
     additionally
    -0.08
     Stout
    -0.08
     Perry
    -0.08
     goodwill
    -0.07
    POSITIVE LOGITS
     softly
    0.13
     till
    0.12
     hearing
    0.11
    ologia
    0.11
     Buchanan
    0.11
     cult
    0.11
     gently
    0.10
    607
    0.10
    daemon
    0.10
     causa
    0.10
    Activations Density 0.156%

    No Known Activations