© 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. 48166
    Prev
    Next
    INDEX
    Explanations

    qualified success

    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
     Aub
    -0.10
    erce
    -0.09
     Más
    -0.09
     Various
    -0.08
    ahr
    -0.08
     ([[
    -0.08
     mest
    -0.08
     Millenn
    -0.08
    _ANY
    -0.08
     various
    -0.08
    POSITIVE LOGITS
     briefly
    0.25
     until
    0.22
     momentarily
    0.21
     Until
    0.19
     superficial
    0.18
     temporarily
    0.18
    until
    0.18
     SOME
    0.18
    Until
    0.17
     upto
    0.17
    Activations Density 0.624%

    No Known Activations