© 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. 48085
    Prev
    Next
    INDEX
    Explanations

    amazed, impressed, staggering

    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
     annoy
    -0.11
     desperately
    -0.11
     bothers
    -0.10
     infuri
    -0.10
     (?)
    -0.10
     Leading
    -0.10
    /inet
    -0.10
     Matlab
    -0.10
    vik
    -0.10
     Tart
    -0.10
    POSITIVE LOGITS
     awe
    0.32
     amazed
    0.27
     marvel
    0.27
     impressed
    0.23
     impressive
    0.21
     amazing
    0.19
     breathtaking
    0.18
     feats
    0.18
     wow
    0.18
     wonders
    0.17
    Activations Density 0.041%

    No Known Activations